Health monitoring method, device and equipment for mixed tower of wind turbine generator and medium
By using big data analysis and intelligent algorithms to assess the health status of wind turbine towers, the problem of insufficient monitoring accuracy and real-time performance in existing technologies has been solved, achieving efficient health monitoring and early warning, and improving the safety and reliability of wind turbines.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-19
- Publication Date
- 2026-03-13
AI Technical Summary
In the existing technology, the health monitoring of wind turbine towers is insufficient in terms of monitoring accuracy, data processing and real-time performance, which affects the stable operation and maintenance efficiency of wind turbines.
By employing big data analytics and intelligent algorithms, the system acquires attribute data and real-time monitoring data of the hybrid tower, performs state assessment using a pre-trained hybrid tower health status assessment model, and generates health monitoring and early warning information when early warning rules are met, including real-time monitoring and analysis of vibration acceleration, strain, temperature, and humidity.
It enables high-precision and efficient health monitoring and early warning of mixed towers, improves the safety and reliability of wind turbine units, and provides timely operation and maintenance guidance.
Smart Images
Figure CN121654565A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of wind turbine health monitoring technology, and more specifically, to a method, device, equipment and medium for health monitoring of a mixed tower of a wind turbine. Background Technology
[0002] With the continuous development of wind power generation technology, hybrid tower health monitoring and condition assessment of wind turbines have become key technologies for improving the reliability and maintenance efficiency of wind power systems. While various health monitoring methods exist, they still have shortcomings in terms of monitoring accuracy, data processing, and real-time performance, affecting the stable operation and maintenance efficiency of wind turbines. Summary of the Invention
[0003] The purpose of this application is to provide a method, device, equipment and medium for health monitoring of mixed towers of wind turbines, so as to solve the above-mentioned problems existing in the prior art, and to achieve high-precision and efficient health monitoring and early warning while ensuring the stable operation of wind turbines.
[0004] Firstly, a method for health monitoring of hybrid towers in wind turbines is provided, the method including: Obtain the attribute data of the hybrid tower of the wind turbine and the real-time monitoring data for the current time period; Based on the attribute data, the real-time monitoring data is analyzed to obtain the state analysis results of the mixing tower; The real-time monitoring data is input into a pre-trained hybrid tower health status assessment model to obtain the hybrid tower status assessment result; wherein, the hybrid tower health status assessment model is trained based on historical monitoring data of the hybrid tower at multiple historical moments; Based on the state analysis results and the state assessment results, the health monitoring results of the mixing tower are generated; If the status analysis result or the status assessment result meets the configured early warning rules, then health monitoring early warning information for the hybrid tower is generated.
[0005] In an optional implementation, the real-time monitoring data includes: vibration acceleration time history curves of the hybrid tower in different directions, strain data at different locations of the hybrid tower, temperature data and humidity data, as well as the first displacement of the foundation section of the hybrid tower and the second displacement of the top hub section of the hybrid tower facing the prevailing wind direction. The attribute data includes: the geometric parameters of the hybrid tower, the moment of inertia of the cross section, the reference temperature and reference humidity at different locations of the hybrid tower, the design length of the structural segment to which different locations of the hybrid tower belong, the constitutive relationship of the hybrid tower material, the allowable stress, the coefficient of thermal expansion and humidity sensitivity parameters, and the total height of the hybrid tower.
[0006] In an optional implementation, the real-time monitoring data is analyzed based on the attribute data to obtain the state analysis results of the mixing tower, including: The vibration acceleration time history curves of the mixing tower in different directions were analyzed to obtain the vibration acceleration analysis results; Based on the moment of inertia of the cross section of the hybrid tower and the constitutive relationship and allowable stress of the hybrid tower material, the strain data at different locations of the hybrid tower are analyzed to obtain stress analysis results. Based on the geometric parameters of the mixing tower, the reference temperature and humidity at different locations of the mixing tower, and the thermal expansion coefficient and humidity sensitivity parameters of the mixing tower materials, the temperature and humidity data at different locations of the mixing tower are analyzed to obtain the environmental impact analysis results. The tilt displacement of the mixing tower is calculated based on the total height of the mixing tower and the first and second displacements.
[0007] In an optional implementation, the vibration acceleration analysis results include: the natural frequency and damping ratio of the hybrid tower of the wind turbine; The vibration acceleration time history curves of the mixing tower in different directions were analyzed to obtain the vibration acceleration analysis results, including: The vibration acceleration time history curves of the hybrid tower of the wind turbine in different directions are filtered and baseline corrected to obtain the preprocessed vibration acceleration time history curves. The preprocessed vibration acceleration time history curve is converted into a power spectral density curve in the frequency domain using fast Fourier transform. The power spectral density curve was analyzed to determine the natural frequency and damping ratio of the mixing tower.
[0008] In an optional implementation, the stress analysis results include the stress distribution inside the hybrid tower of the wind turbine and the bending moment and overall strength of the hybrid tower. Based on the moment of inertia of the cross-section of the hybrid tower and the constitutive relationship and allowable stress of the hybrid tower material, strain data at different locations of the hybrid tower are analyzed to obtain stress analysis results, including: Based on the initial strain values at different locations of the configured mixing tower and the constitutive relationship of the mixing tower material, the reference stress at different locations of the mixing tower is calculated. Based on the strain data at different locations in the mixing tower and the constitutive relationship of the mixing tower material, the total stress value at different locations in the mixing tower is calculated; Based on the total stress value and the corresponding reference stress at different locations in the mixing tower, calculate the additional stress value at different locations in the mixing tower. By extending the total stress values at different locations in the mixing tower to the entire mixing tower, the total stress distribution inside the mixing tower is obtained. The total stress at different parts of the mixing tower is obtained from the total stress distribution inside the mixing tower. Based on the allowable stress of the mixed tower materials and the strength criteria of the configuration, it is determined whether the total stress of each part of the mixed tower exceeds the allowable stress, and the strength verification result is obtained. Based on the strength verification results and the total stress distribution inside the hybrid tower, it is determined whether the hybrid tower meets the static equilibrium conditions of the configuration, and the stability assessment results of the hybrid tower are obtained. Based on the moment of inertia of the cross section, the additional stress values at different locations of the hybrid tower, and the distances from the different locations to the neutral axis of the hybrid tower, the bending moments at different locations of the hybrid tower are calculated.
[0009] In one optional implementation, based on the geometric parameters of the mixing tower, the reference temperature and humidity at different locations within the mixing tower, and the thermal expansion coefficient and humidity sensitivity parameters of the mixing tower materials, temperature and humidity data at different locations within the mixing tower are analyzed to obtain environmental impact analysis results, including: For any mixing tower location, the temperature change of the mixing tower location during the current time period is calculated based on the reference temperature of the mixing tower location and the temperature data of the mixing tower location during the current time period. Based on the baseline humidity at the mixing tower location and the humidity data at the mixing tower location during the current time period, calculate the humidity change at the mixing tower location during the current time period. Based on the design length of the structural segment to which the mixing tower is located, the amount of temperature change, the amount of humidity change, the coefficient of thermal expansion, and the humidity sensitivity parameters, calculate the amount of deformation of the mixing tower location in the current time period. Based on the deformation of each mixing tower location within the current time period, the total deformation of the mixing tower within the current time period is determined, and the total deformation of the mixing tower within the current time period is used as the environmental impact analysis result of the mixing tower.
[0010] In an optional implementation, the tilt displacement of the mixing tower is calculated based on the total height of the mixing tower and the first and second displacements, including: The difference between the first displacement and the second displacement is taken as the tilt angle of the top of the mixing tower; Calculate the horizontal displacement of the top of the mixed tower relative to the foundation section based on the tilt angle of the top of the mixed tower, the total height of the mixed tower, and trigonometric function relationships; The horizontal displacement is defined as the tilt displacement of the mixing tower.
[0011] Secondly, a health monitoring device for the hybrid tower of a wind turbine is provided, the device comprising: The acquisition unit is used to acquire the attribute data of the hybrid tower of the wind turbine and the real-time monitoring data in the current time period; The analysis unit is used to analyze the real-time monitoring data based on the attribute data to obtain the state analysis results of the mixing tower; An evaluation unit is used to input the real-time monitoring data into a pre-trained hybrid tower health status evaluation model to obtain the hybrid tower status evaluation result; wherein, the hybrid tower health status evaluation model is trained based on historical monitoring data of the hybrid tower of the wind turbine at multiple historical moments; A generation unit is used to generate health monitoring results for the mixing tower based on the state analysis results and the state assessment results. An early warning unit is used to generate health monitoring early warning information for the hybrid tower if the status analysis result or the status assessment result meets the configured early warning rules.
[0012] Thirdly, an electronic device is provided, which includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements any of the steps described in the first aspect above.
[0013] Fourthly, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when executed by a processor, the computer program implements the steps of any of the methods described in the first aspect above.
[0014] This application enables comprehensive monitoring of the overall health status of hybrid wind turbine towers. It utilizes big data analytics and intelligent algorithms for real-time data processing and anomaly identification, providing more accurate and timely operation and maintenance guidance to meet the urgent needs of modern wind power systems for efficient and intelligent health monitoring. When the status analysis or assessment results meet the configured early warning rules, rapid tiered early warnings can be issued, thereby achieving accurate assessment of the health status of hybrid wind turbine towers and efficient operation and maintenance, significantly improving the safety and reliability of hybrid wind turbine towers. Attached Figure Description
[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0016] Figure 1 A health monitoring system architecture diagram for a hybrid tower of a wind turbine provided in this application embodiment; Figure 2 This application provides a schematic diagram of the distribution of a mixed-tower data acquisition device. Figure 3This is a schematic diagram of the distribution of a vibration acceleration sensor provided in an embodiment of this application; Figure 4 A schematic diagram of the distribution of a fiber Bragg grating strain sensor provided in an embodiment of this application; Figure 5 A schematic diagram showing the distribution of a temperature sensor and a humidity sensor provided in an embodiment of this application; Figure 6 A schematic diagram of the distribution of an inclinometer provided in an embodiment of this application; Figure 7 A schematic flowchart illustrating a method for health monitoring of a hybrid tower in a wind turbine provided in this application embodiment; Figure 8 A schematic diagram of the structure of a health monitoring device for a hybrid tower of a wind turbine provided in this application embodiment; Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; In the diagram: 1. Hybrid tower; 2. Vibration acceleration sensor; 3. Fiber optic strain sensor; 4. Temperature sensor and humidity sensor; 5. Inclinometer. Detailed Implementation
[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by those skilled in the art. The words "first," "second," and similar terms used in this application do not indicate any order, quantity, or importance, but are only used to distinguish different components. The words "comprising" or "including," etc., mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, but do not exclude other elements or objects. The words "connected," "coupled," or "connected," etc., are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up," "down," "left," "right," etc., are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0018] The health monitoring method for hybrid towers of wind turbines provided in this application embodiment can be applied to... Figure 1 In the system architecture shown, such as Figure 1As shown, the system may include: multiple data acquisition devices, a wireless communication module, and a server; Among them, multiple data acquisition devices include vibration sensors, vibration acceleration sensors, fiber optic strain sensors, temperature sensors, humidity sensors and inclinometers installed at different locations on the hybrid tower of the wind turbine, which are used to monitor the real-time status of the hybrid tower of the wind turbine in the current time period and send the real-time status to the wireless communication module. The wireless communication module is used to send the received real-time status to the server; The server is used to execute the hybrid tower health monitoring method for wind turbines provided in this application embodiment based on the received real-time status. The server can be a physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.
[0019] In one embodiment of this application, the distribution of multiple data acquisition devices in the mixed tower is as follows: Figure 2 As shown; vibration sensors are arranged at the connection surface between the steel tower and the concrete tower, the top nacelle, and the bottom of the tower to monitor vibration data at different locations of the hybrid wind turbine tower in real time; vibration acceleration sensors are arranged on the outer walls of the hybrid tower on the windward, leeward, and perpendicular sides to the windward direction, as shown. Figure 3 As shown; the vibration acceleration sensor uses a high-sensitivity triaxial accelerometer to capture vibration signals of the wind turbine tower in different directions; fiber optic strain sensors are respectively arranged in the key stress areas of the inner wall of the wind turbine tower, including the foundation connection section, the middle transition section and the top hub section, at a total height of three levels, as shown. Figure 4 As shown; multiple fiber optic strain gauges at each height on the inner wall of the hybrid tower are arranged in a ring array with the prevailing wind direction as the reference to ensure coverage of the full circumference stress changes of the key section. In each ring array at each height, the number of gauges is set to 8, covering the entire 360-degree circumference with an angle of 45 degrees. Temperature and humidity sensors are arranged at a height of 5m on the outer wall of the hybrid tower, located on the sides facing the prevailing wind, away from the prevailing wind, and perpendicular to the prevailing wind direction, respectively. Figure 5 As shown, the inclinometers are used to monitor the ambient temperature and humidity of the mixing tower; the inclinometers are respectively set on the main windward side of the foundation section and the top hub section of the mixing tower, as shown. Figure 6 As shown, the inclinometer has a resolution of 0.01° and a dynamic response frequency of 10Hz, and is used to measure the overall tilt angle of the mixing tower.
[0020] In another embodiment of this application, the temperature sensor and humidity sensor collect the ambient temperature and humidity once per hour, and the environmental impact assessment cycle is calculated on a 24-hour rolling basis.
[0021] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.
[0022] Figure 7 This is a flowchart illustrating a health monitoring method for a hybrid tower wind turbine provided in an embodiment of this application. Figure 7 As shown, the method may include: Step S710: Obtain the attribute data of the hybrid tower of the wind turbine and the real-time monitoring data in the current time period.
[0023] The real-time monitoring data includes: vibration acceleration time history curves of the hybrid tower in different directions, strain data, temperature data, and humidity data at different locations of the hybrid tower, as well as the first displacement of the foundation section of the hybrid tower and the second displacement of the top hub section of the hybrid tower facing the prevailing wind direction; the attribute data includes: geometric parameters of the hybrid tower, moment of inertia of the cross section, reference temperature and reference humidity at different locations of the hybrid tower, design length of the structural section to which different locations of the hybrid tower belong, constitutive relation of the hybrid tower material, allowable stress, coefficient of thermal expansion and humidity sensitivity parameters, and total height of the hybrid tower; the reference temperature and reference humidity at different locations of the hybrid tower are the design reference temperature or design reference humidity at different locations of the hybrid tower or the initial temperature or initial humidity monitored at the initial monitoring.
[0024] In practice, the vibration acceleration data monitored in real time at various moments within the current time period are read from vibration acceleration sensors located at different positions on the hybrid tower to obtain vibration acceleration time history curves in different directions of the hybrid tower; strain data is obtained based on fiber optic strain sensors located at different positions on the hybrid tower; temperature and humidity data are obtained based on temperature and humidity sensors located at different positions on the hybrid tower; and the first and second displacements are collected using inclinometers located on the foundation section and the top hub section of the hybrid tower facing the main wind direction.
[0025] Step S720: Analyze the real-time monitoring data based on the attribute data to obtain the state analysis results of the wind turbine tower.
[0026] The state analysis results include: vibration acceleration analysis results, stress analysis results, environmental impact analysis results, and the tilt angle of the top of the hybrid tower; the vibration acceleration analysis results include: the natural frequency and damping ratio of the hybrid tower of the wind turbine; the stress analysis results include the stress distribution inside the hybrid tower of the wind turbine, as well as the bending moment and overall strength of the hybrid tower.
[0027] In practice (1) Analyze the vibration acceleration time history curves of the hybrid tower in different directions to obtain the vibration acceleration analysis results; specifically, filter and baseline correct the vibration acceleration time history curves of the hybrid tower of the wind turbine in different directions to obtain the preprocessed vibration acceleration time history curves; convert the preprocessed vibration acceleration time history curves into power spectral density curves in the frequency domain through fast Fourier transform; the frequency corresponding to the peak of the power spectral density curve is the approximate natural frequency of the hybrid tower of the wind turbine; use modal analysis to analyze the power spectral density curves or frequency domain data, eliminate interference peaks, and determine the natural frequencies of each order of the hybrid tower of the wind turbine; the modal analysis method can be the random subspace method or the peak picking method; based on the free vibration decay segment or through the resonant peak half-power bandwidth method, use the decay characteristics of the preprocessed vibration acceleration time history curves to calculate the damping ratio; (2) Based on the moment of inertia of the cross section of the hybrid tower and the constitutive relationship and allowable stress of the hybrid tower material, the strain data at different positions of the hybrid tower are analyzed to obtain the stress analysis results; specifically, based on the initial strain values at different positions of the hybrid tower and the constitutive relationship of the hybrid tower material, the reference stress at different positions of the hybrid tower is calculated; wherein, the initial strain values at different positions of the hybrid tower are the initial strains monitored at different positions when there is no external load on the hybrid tower; based on the strain data at different positions of the hybrid tower and the constitutive relationship of the hybrid tower material, the total stress value at different positions of the hybrid tower is calculated; based on the total stress value at different positions of the hybrid tower and the corresponding reference stress, the additional stress value at different positions of the hybrid tower is calculated; through the finite element model or interpolation algorithm, the total stress value at different positions of the hybrid tower is extended to the entire hybrid tower to obtain the total stress distribution inside the hybrid tower; from the hybrid tower inside The total stress distribution of the tower is used to obtain the total stress at different parts of the hybrid tower. The stress at different parts includes the maximum principal stress and the stress at critical sections (such as interfaces and variable cross-sections). Based on the allowable stress of the hybrid tower material and the strength criteria of the configuration, it is determined whether the total stress at each part of the hybrid tower exceeds the allowable stress, thus obtaining the strength verification result. If the total stress at each part of the hybrid tower exceeds the allowable stress, the hybrid tower is at risk of local failure. Based on the strength verification result and the total stress distribution inside the hybrid tower, it is determined whether the hybrid tower meets the static equilibrium conditions of the configuration, thus obtaining the stability assessment result of the hybrid tower. If the hybrid tower does not meet the static equilibrium conditions of the configuration, the hybrid tower is at risk of local failure. Based on the moment of inertia of the cross section, the additional stress values at different locations of the hybrid tower, and the distance from different locations of the configuration to the neutral axis of the hybrid tower, the bending moment at different locations of the hybrid tower is calculated. (3) Based on the geometric parameters of the mixing tower, the reference temperature and reference humidity at different locations of the mixing tower, and the thermal expansion coefficient and humidity sensitivity parameters of the mixing tower material, the temperature and humidity data at different locations of the mixing tower are analyzed to obtain the environmental impact analysis results; specifically, for any mixing tower location, the temperature change at the mixing tower location in the current time period is calculated based on the mixing tower reference temperature and the temperature data at the mixing tower location in the current time period; the humidity change at the mixing tower location in the current time period is calculated based on the mixing tower reference humidity and the humidity data at the mixing tower location in the current time period; the deformation at the mixing tower location in the current time period is calculated based on the design length of the structural segment to which the mixing tower location belongs, the temperature change, the humidity change, the thermal expansion coefficient and humidity sensitivity parameters; based on the deformation at each mixing tower location in the current time period, the total deformation of the mixing tower in the current time period is determined, and the total deformation of the mixing tower in the current time period is used as the environmental impact analysis result of the mixing tower; (4) Calculate the tilt displacement of the mixed tower based on the total height of the tower and the first and second displacements; specifically, take the difference between the first and second displacements as the tilt angle of the top of the tower; according to trigonometric relationships, the horizontal displacement of the top of the tower relative to the foundation section can be calculated from the tilt angle of the top of the tower and the total height of the tower: ;in, H represents the horizontal displacement of the top relative to the base section; H represents the total height of the mixing tower. This indicates the tilt angle of the top of the mixing tower.
[0028] Step S730: Input the real-time monitoring data into the pre-trained hybrid tower health status assessment model to obtain the hybrid tower status assessment results.
[0029] Among them, the hybrid tower health status assessment model is trained based on historical monitoring data of the hybrid tower of wind turbines at multiple historical moments.
[0030] Specifically, the hybrid tower health status assessment model includes: The input layer is used to input real-time monitoring data and perform preprocessing such as cleaning, time axis synchronization, standardization mapping, and window segmentation on the real-time monitoring data. The feature extraction layer is used to extract features from real-time monitoring data to obtain vibration features, strain-displacement compatibility features, and environment-structure interaction features. Specifically, a multi-scale one-dimensional convolutional neural network with a self-attention mechanism is used to extract features from the vibration acceleration time history curves of the mixed tower in different directions using a multi-dimensional vibration dynamic encoder to obtain vibration features. Among them, local modes of vibration signals at different time scales are extracted in parallel using convolutional kernels of different sizes, and the self-attention mechanism is used to calculate the correlation between vibration signals in different directions, identify the dominant vibration modes and the coupling relationship of vibrations in different directions, and obtain vibration features that comprehensively characterize the overall dynamic response of the structure. A strain-displacement compatibility encoder was used to extract features from strain data at different locations of the hybrid tower, the first displacement of the foundation section, and the second displacement of the top hub section, resulting in strain-displacement compatibility features. The hybrid tower structure was treated as a graph, with sensor measurement points as nodes. Node features were defined as strain or displacement values, and the connections between nodes were constructed based on their physical locations and structural force transmission paths. A graph neural network directly learned the compatibility relationship between the structure's strain distribution and overall displacement (foundation displacement and top displacement) by transmitting and aggregating information between nodes, obtaining strain-displacement compatibility features to characterize the structural deformation compatibility and overall stiffness. For example, whether the top displacement matches the strain distribution pattern of the tower body.
[0031] An environment-structure interactive encoder was used to extract features from temperature data, humidity data, and the second displacement of the top hub section of the hybrid tower facing the prevailing wind direction using a cross-modal attention network, thus obtaining environment-structure interactive features. Among them, slowly varying environmental parameters such as temperature and humidity were used as environmental conditions, and the dynamic response of the top displacement was used as the object to be adjusted. The cross-modal attention mechanism learned how environmental conditions affect and modulate the displacement response of the structure, resulting in environment-structure interactive features used to characterize the structure's adaptability to environmental loads and time-varying characteristics. The latent feature generation layer generates target latent features based on vibration features, strain-displacement coordination features, and environment-structure interaction features. Based on these target latent features, the layer determines the current overall structural state and calculates the similarity between the current overall structural state and multiple healthy states in historical data, as well as the probability that the current overall structural state belongs to a healthy cluster. The target latent features include: anomaly precursor features, smoothness features, multi-scale trend features, decoded attenuation trend features, healthy baseline features, latent trend coordination features, and cross-condition adaptive features. Specifically, it decodes anomaly precursor features, smoothness features, and multi-scale trend features from vibration features; decodes attenuation trend features and healthy baseline features from strain-displacement coordination features; and decodes latent trend coordination features and cross-condition adaptive features from environment-structure interaction features. Among them, the anomaly precursor feature is used to find small, persistent deviations from historical healthy vibration patterns, indicating the accumulation of potential damage; the smoothness feature is used to assess the smoothness of the vibration signal, and sudden spikes or jitters may indicate loose connections or impacts; the multi-scale trend feature is used to characterize the distribution and long-term variation trend of vibration energy in different frequency bands (such as low-frequency overall oscillation and high-frequency local vibration); the decoded attenuation trend feature is used to characterize the attenuation rate of structural vibration and deformation after excitation such as wind load, and slower attenuation may indicate a decrease in structural damping characteristics; the healthy baseline feature is used to characterize the linear or nonlinear relationship that strain and displacement should satisfy under the current load; the implicit trend synergy feature is used to characterize and assess the stability of the relationship between environmental parameters and structural response; and the cross-condition adaptability feature is used to quantify whether the structure's response is still within the expected adaptability range under different temperature and humidity combinations. The parallel inference layer is used to quantify and evaluate the latent features of the target, obtaining preliminary quantitative values of the health status. These preliminary quantitative values include: environmental and structural response synergy, anomaly precursor accumulation index, health baseline deviation, multi-scale trend stability score, latent feature decay health, cross-condition adaptability score, temporal latent feature smoothness score, latent feature clustering consistency score, and preliminary health score. Specifically, latent trend synergy features are input into a trained environmental-structural response synergy baseline model to obtain the environmental and structural response synergy; anomaly precursor features are input into a multi-dimensional probability distribution model trained using healthy vibration features to calculate the probability density value of their belonging to the healthy distribution, obtaining the anomaly precursor accumulation index; healthy baseline features are input into a trained strain-displacement relationship prediction model to obtain the health baseline deviation; and based on the baseline entropy range of energy distribution in each frequency band under healthy conditions, entropy spectrum calculation and stability evaluation are performed on the multi-scale trend features to obtain... Multi-scale trend stability score; based on the damping ratio benchmark value and its normal fluctuation range of the health status, the attenuation trend characteristics are analyzed to obtain the latent feature attenuation health score; based on the upper and lower bounds of the health envelope of the structural response (such as top displacement) under different configured environmental conditions (temperature-humidity zoning), the cross-condition adaptability characteristics are analyzed to obtain the cross-condition adaptability score; based on the smoothness benchmark threshold of the health status signal, the smoothness characteristics are evaluated to obtain the temporal latent feature smoothness score; based on the clustering centers and typical distance distribution formed by the health status samples in the feature space, the clustering consistency characteristics are calculated to obtain the latent feature clustering consistency score; a lightweight regression neural network is used to fuse the environmental and structural response synergy, the cumulative index of abnormal precursors, the health baseline deviation, the multi-scale trend stability score, the latent feature attenuation health score, the cross-condition adaptability score, the temporal latent feature smoothness score, and the latent feature clustering consistency score to obtain a preliminary health score; The health trend scoring layer is used to adaptively weight and fuse the preliminary quantitative values of health status to obtain a health trend score; calculate the contribution of different preliminary quantitative values of health status to the health trend score; and mark the parameters contained in the features corresponding to the preliminary quantitative values of health status with the highest contribution and low scores as the current main risk sources. The health trajectory prediction layer is used to input the current health trend score into the trained health trend prediction model to obtain the predicted health trend score for a preset future time period. The output layer is used to output health assessment results, which include: health trend score, contribution of preliminary quantitative values of different health states to the health trend score, and predicted health trend score.
[0032] Among them, the relevant data on health status are historical data in which the health monitoring results were healthy.
[0033] Step S740: Based on the status analysis results and status assessment results, generate the health monitoring results of the hybrid tower.
[0034] In practice, the state analysis results and state evaluation results of the hybrid tower in the current time period are determined as the health monitoring results of the hybrid tower; when both the state analysis results and the state evaluation results are within the score range corresponding to the configured health status, the health monitoring result is healthy.
[0035] Step S750: If the status analysis result or status assessment result meets the configured early warning rules, then generate health monitoring early warning information for the hybrid tower.
[0036] In practice, the early warning rules include the natural frequency safety range, the total stress distribution safety range inside the hybrid tower, the bending moment safety range, the total deformation safety range, the tilt angle safety range at the top of the hybrid tower, the health trend score safety range, and the predicted health trend score safety range. If any parameter or result in the state analysis results or state assessment results does not meet the corresponding safety range, an early warning message is generated. At the same time, the difference between the parameter or result and the safety range is calculated, and the configured early warning level is determined based on the difference. The early warning level and the early warning message are then issued according to the early warning method corresponding to the corresponding early warning level. For example, if the natural frequency safety range of a hybrid tower is 0.5Hz to 1.5Hz, and the monitored natural frequency is lower than 0.4Hz or higher than 1.6Hz, a level one early warning is triggered. Or, if the yield strength of the hybrid tower material is 250MPa, and the stress value calculated at a certain measuring point reaches 260MPa, an early warning message is immediately generated and pushed to the operation and maintenance personnel via mobile terminal.
[0037] Corresponding to the above method, this application also provides a health monitoring device for the hybrid tower of a wind turbine, such as... Figure 8 As shown, the device includes: The acquisition unit 810 is used to acquire the attribute data of the hybrid tower of the wind turbine and the real-time monitoring data in the current time period; Analysis unit 820 is used to analyze real-time monitoring data based on attribute data to obtain the state analysis results of the mixing tower; The evaluation unit 830 is used to input real-time monitoring data into a pre-trained hybrid tower health status evaluation model to obtain the hybrid tower status evaluation result; wherein, the hybrid tower health status evaluation model is trained based on historical monitoring data of the hybrid tower of the wind turbine at multiple historical moments. The generation unit 840 is used to generate health monitoring results for the mixing tower based on the state analysis results and state assessment results; The early warning unit 850 is used to generate health monitoring early warning information for the hybrid tower if the status analysis result or status assessment result meets the configured early warning rules.
[0038] The functions of each functional unit of the health monitoring device for the mixed tower of wind turbine provided in the above embodiments of this application can be realized through the above methods and steps. Therefore, the specific working process and beneficial effects of each unit in the health monitoring device for the mixed tower of wind turbine provided in the embodiments of this application will not be repeated here.
[0039] This application also provides an electronic device, such as... Figure 9 As shown, it includes a processor 910, a communication interface 920, a memory 930, and a communication bus 940, wherein the processor 910, the communication interface 920, and the memory 930 communicate with each other through the communication bus 940.
[0040] Memory 930 is used to store computer programs; When the processor 910 executes the program stored in the memory 930, it performs the following steps: Obtain the attribute data of the hybrid tower of the wind turbine and the real-time monitoring data for the current time period; Based on the attribute data, the real-time monitoring data is analyzed to obtain the state analysis results of the mixing tower; Real-time monitoring data is input into a pre-trained hybrid tower health status assessment model to obtain the hybrid tower status assessment results; the hybrid tower health status assessment model is trained based on historical monitoring data of the hybrid tower of the wind turbine at multiple historical moments; Based on the results of the condition analysis and condition assessment, health monitoring results for the hybrid tower are generated; If the status analysis results or status assessment results meet the configured early warning rules, health monitoring early warning information for the hybrid tower will be generated.
[0041] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.
[0042] The communication interface is used for communication between the aforementioned electronic devices and other devices.
[0043] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.
[0044] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0045] The implementation methods and beneficial effects of the various components of the electronic device in the above embodiments for solving the problem can be found in [reference needed]. Figure 7 The steps in the illustrated embodiments are used to implement the electronic device. Therefore, the specific working process and beneficial effects of the electronic device provided in this application will not be repeated here.
[0046] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform the health monitoring method for the hybrid tower of any of the wind turbine units described in the above embodiments.
[0047] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute the health monitoring method for the hybrid tower of any of the wind turbine units described in the above embodiments.
[0048] Those skilled in the art will understand that the embodiments in this application can be provided as methods, systems, or computer program products. Therefore, the embodiments in this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments in this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0049] This application describes embodiments of methods, apparatus (systems), and computer program products according to embodiments of this application with reference to flowchart illustrations and / or block diagrams. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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 processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0050] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0051] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0052] Although preferred embodiments have been described in this application, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of this application.
[0053] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of the embodiments of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of this application and its equivalents, then these modifications and variations are also intended to be included in the embodiments of this application.
Claims
1. A method for health monitoring of hybrid towers in wind turbine units, characterized in that, The method includes: Obtain the attribute data of the hybrid tower of the wind turbine and the real-time monitoring data for the current time period; Based on the attribute data, the real-time monitoring data is analyzed to obtain the state analysis results of the mixing tower; The real-time monitoring data is input into a pre-trained hybrid tower health status assessment model to obtain the hybrid tower status assessment result; wherein, the hybrid tower health status assessment model is trained based on historical monitoring data of the hybrid tower at multiple historical moments; Based on the state analysis results and the state assessment results, the health monitoring results of the mixing tower are generated; If the status analysis result or the status assessment result meets the configured early warning rules, then health monitoring early warning information for the hybrid tower is generated.
2. The method as described in claim 1, characterized in that, The real-time monitoring data includes: vibration acceleration time history curves of the hybrid tower in different directions, strain data, temperature data, and humidity data at different locations of the hybrid tower, as well as the first displacement of the foundation section of the hybrid tower and the second displacement of the top hub section of the hybrid tower facing the prevailing wind direction. The attribute data includes: the geometric parameters of the hybrid tower, the moment of inertia of the cross section, the reference temperature and reference humidity at different locations of the hybrid tower, the design length of the structural segment to which different locations of the hybrid tower belong, the constitutive relationship of the hybrid tower material, the allowable stress, the coefficient of thermal expansion and humidity sensitivity parameters, and the total height of the hybrid tower.
3. The method as described in claim 2, characterized in that, Based on the attribute data, the real-time monitoring data is analyzed to obtain the state analysis results of the mixing tower, including: The vibration acceleration time history curves of the mixing tower in different directions were analyzed to obtain the vibration acceleration analysis results; Based on the moment of inertia of the cross section of the hybrid tower and the constitutive relationship and allowable stress of the hybrid tower material, the strain data at different locations of the hybrid tower are analyzed to obtain stress analysis results. Based on the geometric parameters of the mixing tower, the reference temperature and humidity at different locations of the mixing tower, and the thermal expansion coefficient and humidity sensitivity parameters of the mixing tower materials, the temperature and humidity data at different locations of the mixing tower are analyzed to obtain the environmental impact analysis results. The tilt displacement of the mixing tower is calculated based on the total height of the mixing tower and the first and second displacements.
4. The method as described in claim 3, characterized in that, The vibration acceleration analysis results include: the natural frequency and damping ratio of the hybrid tower of the wind turbine; The vibration acceleration time history curves of the mixing tower in different directions were analyzed to obtain the vibration acceleration analysis results, including: The vibration acceleration time history curves of the hybrid tower of the wind turbine in different directions are filtered and baseline corrected to obtain the preprocessed vibration acceleration time history curves. The preprocessed vibration acceleration time history curve is converted into a power spectral density curve in the frequency domain using fast Fourier transform. The power spectral density curve was analyzed to determine the natural frequency and damping ratio of the mixing tower.
5. The method as described in claim 3, characterized in that, The stress analysis results include the stress distribution inside the hybrid tower of the wind turbine, as well as the bending moment and overall strength of the hybrid tower. Based on the moment of inertia of the cross-section of the hybrid tower and the constitutive relationship and allowable stress of the hybrid tower material, strain data at different locations of the hybrid tower are analyzed to obtain stress analysis results, including: Based on the initial strain values at different locations of the configured mixing tower and the constitutive relationship of the mixing tower material, the reference stress at different locations of the mixing tower is calculated. Based on the strain data at different locations in the mixing tower and the constitutive relationship of the mixing tower material, the total stress value at different locations in the mixing tower is calculated; Based on the total stress value and the corresponding reference stress at different locations in the mixing tower, calculate the additional stress value at different locations in the mixing tower. By extending the total stress values at different locations in the mixing tower to the entire mixing tower, the total stress distribution inside the mixing tower is obtained. The total stress at different parts of the mixing tower is obtained from the total stress distribution inside the mixing tower. Based on the allowable stress of the mixed tower materials and the strength criteria of the configuration, it is determined whether the total stress of each part of the mixed tower exceeds the allowable stress, and the strength verification result is obtained. Based on the strength verification results and the total stress distribution inside the hybrid tower, it is determined whether the hybrid tower meets the static equilibrium conditions of the configuration, and the stability assessment results of the hybrid tower are obtained. Based on the moment of inertia of the cross section, the additional stress values at different locations of the hybrid tower, and the distances from the different locations to the neutral axis of the hybrid tower, the bending moments at different locations of the hybrid tower are calculated.
6. The method as described in claim 3, characterized in that, Based on the geometric parameters of the mixing tower, the reference temperature and humidity at different locations within the mixing tower, and the thermal expansion coefficient and humidity sensitivity parameters of the mixing tower materials, the temperature and humidity data at different locations within the mixing tower are analyzed to obtain the environmental impact analysis results, including: For any mixing tower location, the temperature change of the mixing tower location during the current time period is calculated based on the reference temperature of the mixing tower location and the temperature data of the mixing tower location during the current time period. Based on the baseline humidity at the mixing tower location and the humidity data at the mixing tower location during the current time period, calculate the humidity change at the mixing tower location during the current time period. Based on the design length of the structural segment to which the mixing tower is located, the amount of temperature change, the amount of humidity change, the coefficient of thermal expansion, and the humidity sensitivity parameters, calculate the amount of deformation of the mixing tower location in the current time period. Based on the deformation of each mixing tower location within the current time period, the total deformation of the mixing tower within the current time period is determined, and the total deformation of the mixing tower within the current time period is used as the environmental impact analysis result of the mixing tower.
7. The method as described in claim 2, characterized in that, Based on the total height of the mixing tower and the first and second displacements, the tilt displacement of the mixing tower is calculated, including: The difference between the first displacement and the second displacement is taken as the tilt angle of the top of the mixing tower; Calculate the horizontal displacement of the top of the mixed tower relative to the foundation section based on the tilt angle of the top of the mixed tower, the total height of the mixed tower, and trigonometric function relationships; The horizontal displacement is defined as the tilt displacement of the mixing tower.
8. A health monitoring device for the hybrid tower of a wind turbine, characterized in that, The device includes: The acquisition unit is used to acquire the attribute data of the hybrid tower of the wind turbine and the real-time monitoring data in the current time period; The analysis unit is used to analyze the real-time monitoring data based on the attribute data to obtain the state analysis results of the mixing tower; An evaluation unit is used to input the real-time monitoring data into a pre-trained hybrid tower health status evaluation model to obtain the hybrid tower status evaluation result; wherein, the hybrid tower health status evaluation model is trained based on historical monitoring data of the hybrid tower of the wind turbine at multiple historical moments; A generation unit is used to generate health monitoring results for the mixing tower based on the state analysis results and the state assessment results. An early warning unit is used to generate health monitoring early warning information for the hybrid tower if the status analysis result or the status assessment result meets the configured early warning rules.
9. An electronic device, characterized in that, The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.