Intelligent monitoring system, method and equipment for prestress of wind power reinforced concrete tower drum and medium

Abstract

The invention relates to the technical field of wind power prestress monitoring, in particular to an intelligent monitoring system, method, equipment and medium for the prestress of a wind power reinforced concrete tower drum, and the system comprises a monitoring module which is used for obtaining multi-source structure state data from a plurality of sensors on the wind power reinforced concrete tower drum; the processing unit is connected with the monitoring module; the processing unit is configured to perform data processing on the multi-source structure state data; based on the processed multi-source structure state data, constructing a prestress state evaluation model used for representing an association relationship between the prestress data and the structure health index data; and according to an output result of the prestress state evaluation model, triggering a multi-stage early warning module, and generating an early warning signal corresponding to the output result. By constructing a multi-sensor fusion monitoring network, correlation analysis of prestress data and structural health indexes is realized, and a comprehensive basis is provided for safety assessment and maintenance of the tower drum structure.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power prestress monitoring, in particular to an intelligent monitoring system for prestressing of a wind power steel-concrete tower. Background Art

[0002] The steel-concrete tower of a wind turbine, that is, the tower of a wind turbine, is composed of steel and concrete. The lower part of the tower system is a concrete section, and the upper part is a steel tower section, which are connected into a whole by prestressed steel strands. During the operation of the wind turbine, it will be affected by complex loads such as wind load, gravity, and earthquake. These loads may cause changes in prestress. By monitoring the prestress, the stress state of the tower under various working conditions can be understood in real time, providing a basis for safety assessment and maintenance of the structure, and ensuring that the tower remains safe and stable in a long-term and complex service environment.

[0003] Existing prestress monitoring for steel-concrete wind turbine towers suffers from the following technical deficiencies: Traditional manual detection methods (handheld vibrating wire data collectors) are susceptible to significant environmental interference and rely entirely on offline equipment, resulting in poor data accuracy. Furthermore, manual data collection requires significant data volumes and is unable to capture subtle changes in prestress in the strands in real time. Data from individual sensors lacks systematic integration, making it difficult to correlate and analyze the coupling relationship between prestress loss and other parameters such as structural displacement and vibration. Manual inspections are time-consuming, resulting in delayed detection of potential hazards and the inability to automatically link early warnings with maintenance work orders. Summary of the Invention

[0004] In view of the above problems or problems existing in the prior art, the present invention is proposed.

[0005] Therefore, the technical problem to be solved by the present invention is how to obtain multi-source structural status data including prestress data and structural health indicator data, and construct a prestress status assessment model for characterizing the correlation between the aforementioned different data, and then trigger multi-level early warning based on the analysis results of the model, thereby solving the problems in the existing technology that are difficult to conduct systematic evaluation due to isolated data, and low operation and maintenance efficiency due to the lack of an automated mechanism.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an intelligent monitoring system for prestressing of a wind power steel-concrete tower, wherein the monitoring module is configured to obtain multi-source structural status data from multiple sensors on the wind power steel-concrete tower; the multi-source structural status data includes at least prestressing data and structural health index data of the wind power steel-concrete tower; a processing unit is connected to the monitoring module; the processing unit is configured to: perform data processing on the multi-source structural status data; based on the processed multi-source structural status data, construct a prestressing state evaluation model for characterizing the correlation between the prestressing data and the structural health index data; according to the output result of the prestressing state evaluation model, trigger a multi-level early warning module to generate an early warning signal corresponding to the output result.

[0008] As a preferred solution of the intelligent monitoring system for prestressed steel-concrete tower of wind power plant described in the present invention, the structural health index data includes at least one of tower tilt data obtained by an inclination sensor, tower displacement data obtained by a displacement sensor, and tower vibration data obtained by a vibration sensor.

[0009] As a preferred solution of the intelligent monitoring system for prestressed steel-concrete tower of wind power plant described in the present invention, the data processing performed by the processing unit on the multi-source structural status data includes: performing at least one of filtering processing and temperature compensation processing on the multi-source structural status data.

[0010] As a preferred solution of the intelligent monitoring system for prestressing of a wind power steel-concrete tower described in the present invention, the prestressing data is obtained by directly measuring with a vibrating wire prestressing sensor arranged in the anchoring section of the steel strand; or by obtaining the vibration frequency through an acceleration sensor arranged on the steel strand, and determining it based on a preset frequency difference method calculation formula.

[0011] As a preferred solution of the intelligent monitoring system for prestressed steel-concrete tower of wind power plant described in the present invention, the multi-level warning module includes at least two warning thresholds; the processing unit is specifically configured to: generate a first-level warning signal if the output result of the prestressed state assessment model reaches a first warning threshold; and generate a second-level warning signal if the output result reaches a second warning threshold higher than the first warning threshold.

[0012] As a preferred solution of the intelligent monitoring system for prestressed steel-concrete tower of a wind power plant described in the present invention, it also includes a visualization module, which is configured to locate and visualize the output results of the prestressed state assessment model in combination with the building information model of the wind power steel-concrete tower.

[0013] As a preferred solution of the wind power steel-concrete tower prestressed intelligent monitoring system described in the present invention, wherein: the processing unit is also configured to respond to the early warning signal to automatically generate an operation and maintenance work order, and the wind power steel-concrete tower prestressed intelligent monitoring system also includes a communication unit, which is connected to the processing unit and is used to transmit the early warning signal and the operation and maintenance work order to the remote monitoring terminal.

[0014] In a second aspect, the present invention provides a method for intelligently monitoring prestressed steel-concrete towers of wind power plants, comprising:

[0015] Acquire multi-source structural status data from a plurality of sensors on the wind power steel-concrete tower, wherein the multi-source structural status data includes at least prestress data and structural health index data of the wind power steel-concrete tower;

[0016] performing data processing on the multi-source structural state data;

[0017] Based on the processed multi-source structural state data, a prestress state assessment model is constructed for characterizing the correlation between the prestress data and the structural health index data;

[0018] According to the output result of the prestress state assessment model, a multi-level early warning module is triggered to generate an early warning signal corresponding to the output result.

[0019] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the steps of an intelligent monitoring system for prestressed steel-concrete towers of wind power plants.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of an intelligent monitoring system for prestressed steel-concrete towers of wind power plants.

[0021] Beneficial effects of the present invention: The present invention arranges a variety of high-precision sensors in the wind power steel-concrete tower, combines data units to realize real-time collection of prestressed signals by sensors, and uses processing units to perform data fusion, trend analysis and construct a prestressed state assessment model to meet the needs of accurate deformation monitoring. At the same time, with the help of multi-level early warning modules, second-level alarms are achieved, which significantly improves the timeliness of hidden danger discovery. Compared with traditional detection methods, it can accurately monitor prestress changes in real time, accurately capture subtle changes in steel strand prestress in real time, effectively improve monitoring accuracy, and meet millimeter-level deformation monitoring needs; compared with a single sensor monitoring method, by constructing a multi-sensor fusion monitoring network, correlation analysis between prestressed data and structural health indicators is achieved, providing a comprehensive basis for tower structure safety assessment and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 This is a schematic diagram of the monitoring point settings for an intelligent monitoring system for prestressed steel-concrete towers of wind turbines.

[0024] Figure 2 This is a schematic diagram of the installation position of the tilt sensor of a wind power steel-concrete tower prestressed intelligent monitoring system.

[0025] Figure 3 This is a schematic diagram from another perspective of the installation position of the tilt sensor of a wind power steel-concrete tower prestressed intelligent monitoring system.

[0026] Figure 4 This is a schematic diagram of the installation position of vibration sensors in a wind turbine steel-concrete tower prestressed intelligent monitoring system.

[0027] Figure 5 This is a schematic diagram of the installation position of the displacement sensor of a wind power steel-concrete tower prestressed intelligent monitoring system.

[0028] Figure 6 This is a schematic diagram of the installation position of the cable force sensor of a wind power steel-concrete tower prestressed intelligent monitoring system.

[0029] Figure 7 This is a system topology diagram of a wind power steel-concrete tower prestressed intelligent monitoring system. DETAILED DESCRIPTION

[0030] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0031] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0032] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0033] Example 1, reference Figures 1 to 7 , which is the first embodiment of the present invention, provides an intelligent monitoring system for prestressed steel-concrete towers of wind power plants. In practical applications, the system is mainly composed of a monitoring module and a processing unit.

[0034] In the embodiments of this application, the monitoring module is configured to acquire multi-source structural status data from multiple sensors on the wind turbine steel-concrete tower. To achieve full coverage of the tower's lifecycle, from construction to long-term service, the monitoring module adopts different monitoring strategies at different stages.

[0035] For example, during the construction and prestressing stage, to directly obtain high-precision initial prestressing data, the monitoring module includes a pressure-type cable tension sensor arranged at the anchor section of the steel strand, such as the BY-YYL-11 type, or a sensor with a different range, such as 2000KN, which can be customized according to the designed prestressing force. The vibrating string signal is collected in real time through a vibrating string collector of the centralized online monitoring system, such as the BY-STD1000A type. During the long-term operation stage of the tower, the monitoring module includes an acceleration-type cable tension sensor, such as the BY-P12H type, fixed to the steel strand anti-fall net. A dynamic data collector, such as the BY-D3000B type, is used to synchronously monitor the vibration frequency of the steel strand and then calculate the cable tension using the frequency difference method.

[0036] At the same time, no matter at which stage, the monitoring module also uses the inclination sensors, displacement sensors and vibration sensors arranged on the tower to synchronously collect the tower inclination, displacement and vibration status information as structural health indicator data.

[0037] In an optional embodiment, the monitoring module can also utilize distributed fiber optic sensing technology. Distributed fiber optic sensing technology operates on the principle that the optical fiber itself serves as both the signal transmission medium and the sensing element. For example, fiber Bragg grating (FBG) sensors or Brillouin optical time-domain analysis (BOTDA) sensing cables can be deployed along the entire length of the prestressed steel strand. FBG sensors contain a grating with a specific period that reflects only light of a specific wavelength. Therefore, when the optical fiber undergoes physical deformation due to strain or temperature changes, the grating period changes, causing the central wavelength of the reflected light to shift. Therefore, by demodulating this wavelength shift, the strain and temperature values ​​at each measuring point along the cable can be inversely calculated. With BOTDA technology, the frequency of Brillouin scattered light generated during optical fiber transmission is linearly related to the strain and temperature of the fiber. Therefore, by injecting pulsed light into the sensing cable and detecting the frequency of the backscattered light, a continuous strain and temperature profile along the entire length of the cable can be obtained. Because these two fiber optic sensing technologies can obtain data distributed continuously along the length of the steel strand, the processing unit can more accurately identify local stress concentration points and temperature anomaly areas, thereby providing higher-resolution input data for subsequent condition assessment models.

[0038] In another optional embodiment, the monitoring module can also utilize displacement monitoring technology based on the Global Navigation Satellite System (GNSS), eliminating most of the errors in satellite signal propagation through differential calculations. Specifically, high-precision GNSS receivers are installed at the tower top and at key elevations as rover stations, while a GNSS base station is established in a stable area on the ground. Because the base station and rover receive the same set of satellite signals and the base station's precise coordinates are known, the base station can calculate the propagation errors of the satellite signals. By transmitting this error correction information to the rover at the tower top in real time, the rover eliminates the shared error terms and calculates its own three-dimensional coordinates relative to the base station. Therefore, this displacement monitoring technology can obtain absolute displacement, sway trajectory, and vibration displacement of key tower components with millimeter-level accuracy, around the clock. Because these macroscopic structural response data directly reflect the tower's overall posture and stiffness state, they are input into the processing unit as important structural health indicators. Correlated analysis with local prestressing data enables a more comprehensive assessment of the tower's overall stability.

[0039] Furthermore, the processing unit, as the intelligent core of the system, establishes data connection with the monitoring module, receives and processes all multi-source structural status data.

[0040] For example, the processing unit's software architecture can be built based on SpringCloud microservices and deployed on a cloud platform with elastic computing and distributed storage capabilities. After receiving the raw data, the processing unit first performs data processing, such as filtering and temperature compensation, to eliminate environmental noise and improve data quality. The processing unit then performs its core function: building and applying a prestressed state assessment model. This model aims to deeply explore and characterize the inherent correlations between prestressed data and various structural health indicators. This model can be implemented using a variety of technical approaches.

[0041] In a specific embodiment, the model can be an expert system based on a rule engine, which can quickly judge clear risk patterns through a series of "IF-THEN" logical rules preset by domain experts.

[0042] In another embodiment, the model may also use statistical correlation analysis methods, such as multiple regression analysis or grey correlation analysis, to quantify the mathematical relationship between prestress loss and external factors such as temperature, wind speed, and tower displacement, thereby effectively distinguishing normal fluctuations from abnormal changes.

[0043] After the prestressed state assessment model completes its analysis and outputs its results, the processing unit triggers a multi-level early warning module based on these results. This module can preset multiple, progressively higher risk thresholds. For example, for a particular strand's vibration frequency, three thresholds—1850Hz, 1900Hz, and 1950Hz—are set, triggering warning signals at different levels. The platform's response time can be less than 0.5 seconds, enabling instant alerts for potential hazards.

[0044] The present invention also includes a visualization module and automated operation and maintenance linkage. The visualization module integrates the tower's Building Information Model (BIM) model to provide three-dimensional positioning and visualization of assessment results and warning information. Furthermore, upon triggering a warning signal, the processing unit automatically generates a detailed operation and maintenance work order, which may include the risk location, warning level, and recommended inspection items. Ultimately, the warning signal and operation and maintenance work order are transmitted to a remote monitoring terminal via a communication unit, such as 4G or Ethernet, guiding operation and maintenance personnel in performing precise and efficient maintenance.

[0045] Example 2, reference Figures 1 to 7 This is the second embodiment of the present invention. Based on the first embodiment, the specific implementation method of the wind power steel-concrete tower prestressed intelligent monitoring system is described in detail.

[0046] In an embodiment of the present application, the monitoring module is configured to obtain multi-source structural status data from multiple sensors on the wind power steel-concrete tower; the multi-source structural status data includes at least prestress data and structural health index data of the wind power steel-concrete tower.

[0047] In order to accurately obtain prestressing data, the monitoring module adopts different sensor layout schemes during the construction phase and the operation phase.

[0048] For example, during the construction phase, the monitoring module includes a vibrating wire prestressed sensor arranged in the anchor section of the steel strand. Before the steel strands are bundled, a pressure-type cable tension sensor with model BY-YYL-11 is inserted into the anchor section of the steel strand. The sensor range is customized to 2000KN based on the designed prestress, and a total of 8 sensors are arranged. The working principle of the vibrating wire sensor is as follows: a pre-tensioned steel wire is installed inside the sensor. When the sensor is subjected to an external force, the tension of the steel wire changes, causing its natural vibration frequency to change. The vibrating wire signal is collected in real time by the BY-STD1000A vibrating wire collector of the centralized online monitoring system. The vibrating wire collector is equipped with a 32-bit high-performance floating-point processor and an all-metal casing design, which can monitor the changes in the vibrating wire frequency in a long-term and stable manner. Because tension and frequency are positively correlated, the prestress can be inferred by measuring the frequency change.

[0049] In an optional embodiment, the monitoring module can also use magnetoelastic sensors for prestress monitoring. Magnetoelastic sensors operate based on the magnetoelastic effect of ferromagnetic materials. When a steel strand is subjected to tension, its magnetic permeability changes. By attaching a ring-shaped magnetoelastic sensor to the strand anchorage, applying an alternating magnetic field, and measuring the change in induced voltage, the prestress value can be determined. Because magnetoelastic sensors do not require pre-embedded installation and can be installed on existing structures, they are suitable for prestress monitoring in renovation projects.

[0050] In another optional embodiment, the monitoring module can also use fiber Bragg grating sensors for prestress monitoring. These sensors are affixed to or embedded in the surface of the steel strand. When the strand is stressed and strained, the grating period changes, causing the central wavelength of the reflected light to shift. The wavelength shift is measured using a wavelength demodulator and, combined with a calibration factor, the strain value can be calculated, thereby inferring the prestress. Because fiber optic sensors are resistant to electromagnetic interference, corrosion, and capable of distributed measurement, they offer unique advantages in strong electromagnetic environments or where multi-point monitoring is required.

[0051] For example, during the operation phase, the monitoring module obtains the vibration frequency through the acceleration sensor arranged on the steel strand, and determines the prestress data based on the preset frequency difference method calculation formula. At the steel strand anti-fall net, that is, 5 meters away from the anchor end, the BY-P12H type acceleration sensor is fixed by a clamp, and a total of 8 sensors are arranged. The sensitivity of the acceleration sensor is 1000mV / g. The voltage signal output by the sensor is received by the dynamic data acquisition instrument BY-D3000B to synchronously monitor the vibration frequency of the steel strand. The calculation principle of the frequency difference method is: for the cable fixed at both ends, the relationship between the cable force T and the natural frequency f is T=4mL²f² / n², where m is the mass per unit length of the cable, L is the calculated length of the cable, n is the vibration order, and f is the natural frequency of the corresponding order. By monitoring the change in vibration frequency in real time, the change in cable force can be dynamically calculated.

[0052] In an optional implementation, strain gauge measurement can also be used to monitor prestress during operation. A resistance strain gauge is attached to the surface of the steel strand. When the strand is stressed and strained, the resistance of the strain gauge changes. A Wheatstone bridge circuit converts this resistance change into a voltage signal, which is then amplified and converted to analog-to-digital before being input into a data acquisition system. Due to their high measurement accuracy and fast response speed, strain gauges are suitable for applications requiring high-precision, real-time monitoring.

[0053] In the embodiment of the present application, the structural health index data includes at least one of: tower tilt data obtained by an inclination sensor, tower displacement data obtained by a displacement sensor, and tower vibration data obtained by a vibration sensor. The inclination sensor is used to monitor the inclination angle of the wind power steel-concrete tower in real time. The tower may tilt under complex loads such as wind load, gravity, and earthquake. The inclination sensor can accurately measure the inclination change with an absolute accuracy of 0.003° and a resolution of 0.001°. The displacement sensor is used to monitor the displacement change of the tower structure and can measure the horizontal and vertical displacement of the tower in different directions. The vibration sensor monitors the vibration of the tower and captures the vibration frequency, amplitude and other parameters of the tower in real time.

[0054] For example, the tilt sensors are installed on platforms at different heights of the tower, such as Figure 2 and Figure 3 As shown. The sensor is fixed to the inner wall of the tower through a special bracket to ensure a rigid connection with the tower. Two mutually perpendicular tilt sensors are arranged in each monitoring section to measure the tilt angles in the X and Y directions respectively. Figure 4 As shown in Figure 1, it is installed in the middle and top of the tower to monitor the overall vibration characteristics of the tower. Figure 5 As shown, it is installed at the connection of tower segments to monitor the relative displacement between tower segments.

[0055] In an optional embodiment, the structural health indicator data may also include stress monitoring data. By placing stress sensors, such as vibrating wire strain gauges or fiber Bragg grating (FBG) stress sensors, at key locations on the tower, the tower's stress distribution can be monitored in real time. Because stress concentration is one of the main causes of structural failure, stress monitoring can promptly identify potential structural safety hazards.

[0056] In another optional embodiment, the structural health indicator data may also include environmental parameter data. Temperature sensors, humidity sensors, wind speed and direction sensors, and other sensors can be deployed to monitor the tower's environmental conditions. Because environmental factors significantly impact structural performance, such as thermal expansion and contraction caused by temperature changes and material degradation caused by humidity fluctuations, environmental parameter monitoring facilitates a more accurate assessment of structural health.

[0057] In the embodiments of the present application, the processing unit performs data processing on the multi-source structural state data, including at least one of filtering and temperature compensation. Filtering is used to eliminate noise interference in sensor signals and improve data quality. Temperature compensation is used to eliminate the effects of temperature changes on measurement results and ensure the accuracy of monitoring data.

[0058] Exemplarily, the filtering process employs a multi-stage filtering strategy. First, a hardware filter is used to remove high-frequency noise, with a cutoff frequency set to 100Hz. Then, a Kalman filter algorithm is employed at the software level to establish the system state equation and observation equation, estimate the system state in real time, and effectively filter out random noise. For sudden interference, a median filter algorithm is employed to eliminate outliers by comparing the values ​​of adjacent sampling points.

[0059] Temperature compensation is performed based on the temperature characteristic curve of the sensor. Taking a vibrating wire sensor as an example, its frequency-temperature relationship can be expressed as:

[0060] ;

[0061] ;

[0062] in, is the temperature-compensated frequency value (Hz), that is, the final frequency value used for prestress calculation after temperature correction; is the original frequency value measured by the sensor (Hz); is the temperature compensation coefficient, dimensionless; is the linear temperature coefficient (1 / °C), which characterizes the first-order effect of frequency variation with temperature; is the quadratic temperature coefficient (1 / °C²), which characterizes the second-order effect of frequency variation with temperature; is the temperature difference (℃), calculated as ,in is the current measured temperature, The reference temperature for calibration is usually 20°C. and the quadratic temperature coefficient The frequency compensation coefficient is obtained by performing multi-temperature calibration experiments in a constant temperature chamber. The processing unit automatically calculates the temperature compensation coefficient based on the real-time temperature measurement value and corrects the original frequency data.

[0063] The beneficial effects of this temperature compensation formula in the prestress monitoring of wind turbine steel-concrete towers of the present invention are reflected in the following: the ambient temperature of the wind turbine tower varies greatly, from -30°C to 50°C. Temperature changes can cause the frequency drift of the vibrating string sensor to reach 2% to 5%, directly affecting the prestress measurement accuracy. By introducing quadratic compensation, this temperature compensation formula reduces the compensation error under extreme temperature conditions compared to the traditional method that only uses linear compensation. During the transition period between winter and summer, the daily temperature difference can reach more than 30°C. This compensation algorithm can correct the measurement deviation caused by temperature in real time, ensuring the continuity and comparability of prestress monitoring data, avoiding false warnings caused by temperature changes, and reducing the system's false alarm rate.

[0064] In an optional embodiment, data processing may also include data fusion. Because multiple sensors may monitor the same or related physical quantities, data fusion can improve measurement accuracy and reliability. Data fusion can employ methods such as weighted averaging, Bayesian estimation, or neural networks. For example, for prestress monitoring, the direct measurements from a vibrating wire sensor and the indirect calculations from an accelerometer can be fused to obtain a more reliable prestress estimate by assigning different weights.

[0065] In another optional embodiment, data processing can also include anomaly detection. By establishing a statistical model of normal data, such as a Gaussian distribution model or a time series model, the monitoring data can be detected in real time to see if it deviates from the normal range. When an anomaly is detected, the processing unit will flag the abnormal data and trigger an alarm. Simultaneously, a data validation program will be initiated to determine, through cross-validation, whether it is a sensor failure or a structural anomaly.

[0066] In this embodiment of the present application, a processing unit constructs a prestress state assessment model based on processed multi-source structural state data to characterize the correlation between prestress data and structural health indicator data. This model analyzes the correlation between prestress changes and indicators such as tilt, displacement, and vibration to establish a multi-dimensional structural state assessment system.

[0067] For example, a prestressed state assessment model was constructed using a multivariate regression analysis method. For cable No. 11, when the cable tension frequency was monitored to drop from an initial value of 1950Hz to 1900Hz, the displacement of the tower top was simultaneously observed to increase by 2mm and the main vibration frequency to decrease by 0.5Hz. Regression analysis revealed a linear relationship between the prestress loss rate and the displacement increment, with a correlation coefficient of 0.85. Based on this relationship, an early warning is issued when the displacement monitoring value exceeds the set threshold, even if the prestress monitoring value has not yet reached the warning value.

[0068] In an optional implementation, the prestress state assessment model can also be constructed using machine learning methods. By collecting a large amount of historical monitoring data, including samples of normal and abnormal conditions, a support vector machine or random forest classifier is trained. Input features include prestress value, tilt angle, displacement, vibration frequency, etc., and the output is a structural state classification such as normal, slightly abnormal, or severely abnormal. Because machine learning models can capture nonlinear relationships, they are better able to identify complex coupling effects.

[0069] In another alternative implementation, the prestress state assessment model can also utilize a combination of physical and data-driven models. First, a mechanical model of the tower is established based on finite element analysis, and the structural response under different prestress loss scenarios is calculated. Then, measured data is used to modify the model parameters to ensure that the model's predicted values ​​align with the measured values. By combining physical mechanisms with measured data, the model has both a theoretical basis and practical validation, resulting in higher prediction accuracy.

[0070] In an embodiment of the present application, the multi-level warning module includes at least two warning thresholds; the processing unit is specifically configured to: generate a first-level warning signal if the output result of the prestressed state assessment model reaches a first warning threshold; and generate a second-level warning signal if the output result reaches a second warning threshold that is higher than the first warning threshold.

[0071] For example, using cable 11 as an example, the first warning threshold is set at 1850Hz, corresponding to a yellow alert; the second warning threshold is set at 1900Hz, corresponding to an orange alert; and the third warning threshold is set at 1950Hz, corresponding to a red alert. When the monitoring frequency reaches 1950Hz, the system triggers a yellow alert, prompting operators to pay attention; at 1900Hz, an orange alert is triggered, recommending an inspection; and at 1850Hz, a red alert is triggered, requiring immediate action. Each warning level corresponds to different response measures and processing procedures.

[0072] In an optional embodiment, the warning threshold can also be dynamically adjusted based on environmental conditions. Because environmental factors such as temperature and wind speed can affect structural response, a fixed threshold may result in false alarms or missed alarms. The processing unit uses a correction formula to adjust the warning threshold based on real-time environmental parameters. For example, under high temperature conditions, the steel strands will expand thermally, reducing the cable tension accordingly. In this case, the warning threshold should be appropriately lowered. Under strong wind conditions, the dynamic load increases, and the warning threshold should be appropriately raised.

[0073] In this embodiment of the present application, the system also includes a visualization module configured to locate and visualize the output results of the prestressed state assessment model in conjunction with the building information model of the wind turbine steel-concrete tower. The visualization module uses 3D modeling technology to combine monitoring data with the tower structure model, enabling intuitive display of monitoring information.

[0074] For example, Figure 7 As shown, the visualization screen uses a split-screen display. The left side displays a 3D model of the tower, with each sensor location marked with a color-coded icon. Clicking an icon displays real-time data. The right side displays data trend graphs, including prestress change curves, displacement time history curves, and vibration spectrum graphs. When an anomaly occurs at a monitoring point, the corresponding icon flashes to indicate an alarm, and a detailed information window pops up, displaying the anomaly type, severity, and recommended measures.

[0075] In an embodiment of the present application, the processing unit is also configured to respond to the early warning signal to automatically generate an operation and maintenance work order, and the wind power steel-concrete tower prestressed intelligent monitoring system also includes a communication unit, which is connected to the processing unit and is used to transmit the early warning signal and operation and maintenance work order to the remote monitoring terminal.

[0076] For example, when the system triggers an orange alert, the processing unit automatically generates an operation and maintenance work order. The work order includes the abnormal location (cable No. 11), the abnormality type (prestress loss), the current value (1895Hz), recommended inspection items (cable tension re-measurement, anchorage inspection), and a recommended resolution timeframe (within 48 hours). The work order is sent to the operation and maintenance management platform via 4G or Ethernet and simultaneously pushed to the mobile devices of the relevant personnel. After receiving the work order, the operation and maintenance personnel can provide feedback on the progress and results of the processing via their mobile devices, creating a closed-loop management system.

[0077] Through the above-mentioned multiple implementation methods, the present invention realizes all-round intelligent monitoring of the prestressing of wind turbine steel-concrete towers, solves the problems of insufficient accuracy, data isolation and low operation and maintenance efficiency of traditional monitoring methods, and provides reliable guarantee for the safe operation of wind turbine towers.

[0078] Example 3, reference Figures 1 to 7, which is the third embodiment of the present invention, provides a method for intelligently monitoring the prestressing of a wind power steel-concrete tower, which can further illustrate the implementation steps of an intelligent monitoring system for prestressing of a wind power steel-concrete tower; the method comprises:

[0079] Acquire multi-source structural status data from multiple sensors on the wind turbine steel-concrete tower, where the multi-source structural status data includes at least prestress data and structural health index data of the wind turbine steel-concrete tower;

[0080] Perform data processing on multi-source structural status data;

[0081] Based on the processed multi-source structural state data, a prestress state assessment model is constructed to characterize the correlation between prestress data and structural health index data;

[0082] According to the output results of the prestressed state assessment model, the multi-level early warning module is triggered to generate early warning signals corresponding to the output results.

[0083] It should be noted that when a multi-sensor collaborative acquisition mechanism is employed, comprehensive data on the prestressed state and structural response can be obtained. Vibrating-wire sensors directly measure the preload at the anchor end, while acceleration sensors indirectly infer cable tension changes. The two mutually verify each other, ensuring reliable monitoring even if a single sensor exhibits deviation. Therefore, filtering and temperature compensation eliminate interference from ambient noise and temperature drift, enabling accurate extraction of valid information from the raw signal and laying a solid foundation for subsequent analysis.

[0084] Furthermore, the prestress state assessment model not only analyzes the changing patterns of prestress itself, but also incorporates structural responses such as tilt, displacement, and vibration into the assessment system. When prestress is lost, the tower stiffness decreases, which inevitably leads to increased displacement and changes in vibration characteristics. Therefore, by establishing a multi-parameter correlation model, prestress anomalies can be identified from the overall structural response, achieving a transition from local monitoring to overall assessment. Furthermore, the multi-level early warning mechanism responds according to the severity of the risk, ensuring that major hidden dangers are not missed while avoiding the waste of resources caused by excessive early warnings. Each level of early warning corresponds to clear treatment recommendations, providing a basis for operation and maintenance decisions. The entire method achieves closed-loop management of monitoring, analysis, and early warning, transforming passive periodic inspections into active real-time monitoring, thereby significantly improving the operation and maintenance efficiency and safety level of wind turbine towers.

[0085] Example 4. This embodiment also provides an electronic device comprising a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic device comprises a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface of the electronic device is configured to communicate with an external terminal via wired or wireless communication. Wireless communication can be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a method for dynamic marginal carbon emissions measurement and characteristic fitting for a node. The display of the electronic device can be a liquid crystal display or an electronic ink display. The input device of the electronic device can be a touch layer covering the display, buttons, a trackball, or a touchpad provided on the electronic device housing, or an external keyboard, touchpad, or mouse.

[0086] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method proposed in the above embodiment is implemented.

[0087] The storage medium proposed in this embodiment and the method proposed in the above embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0088] From the above description of the embodiments, those skilled in the art will clearly understand that the present invention can be implemented using software and necessary general-purpose hardware. Of course, it can also be implemented using hardware, but in many cases the former is the preferred embodiment. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This software product can be stored on a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk, or optical disk, and includes instructions for enabling an electronic device (such as a personal computer, server, or network device) to execute the methods of the embodiments of the present invention.

[0089] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent monitoring system for prestressed steel-concrete towers of wind power plants, characterized by: include, A monitoring module configured to obtain multi-source structural status data from a plurality of sensors on the wind power steel-concrete tower; the multi-source structural status data at least includes prestress data and structural health index data of the wind power steel-concrete tower; a processing unit connected to the monitoring module; The processing unit is configured to: performing data processing on the multi-source structural state data; Based on the processed multi-source structural state data, a prestress state assessment model is constructed for characterizing the correlation between the prestress data and the structural health index data; According to the output result of the prestress state assessment model, a multi-level early warning module is triggered to generate an early warning signal corresponding to the output result.

2. The wind power steel-concrete tower prestressed intelligent monitoring system according to claim 1, characterized in that: The structural health index data includes at least one of tower tilt data obtained by a tilt sensor, tower displacement data obtained by a displacement sensor, and tower vibration data obtained by a vibration sensor.

3. The wind power steel-concrete tower prestressed intelligent monitoring system according to claim 2, characterized in that: The data processing performed by the processing unit on the multi-source structural state data includes: performing at least one of filtering processing and temperature compensation processing on the multi-source structural state data.

4. The wind power steel-concrete tower prestressed intelligent monitoring system according to claim 3, characterized in that: The prestressing data are: The stress is directly measured by vibrating wire prestressing sensors arranged at the anchorage section of the steel strand. Alternatively, the vibration frequency is obtained by an acceleration sensor arranged on the steel strand and determined based on a preset frequency difference method calculation formula.

5. The wind power steel-concrete tower prestressed intelligent monitoring system according to claim 4, characterized in that: The multi-level warning module includes at least two warning thresholds; The processing unit is specifically configured to: If the output result of the prestressed state assessment model reaches a first warning threshold, a first level warning signal is generated; If the output result reaches a second warning threshold value that is higher than the first warning threshold value, a second level warning signal is generated.

6. The wind power steel-concrete tower prestressed intelligent monitoring system according to claim 5, characterized in that: It also includes a visualization module, which is configured to locate and visualize the output results of the prestressed state assessment model in combination with the building information model of the wind power steel-concrete tower.

7. The wind power steel-concrete tower prestressed intelligent monitoring system according to claim 6, characterized in that: The processing unit is also configured to respond to the early warning signal to automatically generate an operation and maintenance work order, and the wind power steel-concrete tower prestressed intelligent monitoring system also includes a communication unit, which is connected to the processing unit and is used to transmit the early warning signal and the operation and maintenance work order to the remote monitoring terminal.

8. An intelligent monitoring method for prestressing of a wind power steel-concrete tower, characterized by: include, Acquire multi-source structural status data from a plurality of sensors on the wind power steel-concrete tower, wherein the multi-source structural status data includes at least prestress data and structural health index data of the wind power steel-concrete tower; performing data processing on the multi-source structural state data; Based on the processed multi-source structural state data, a prestress state assessment model is constructed for characterizing the correlation between the prestress data and the structural health index data; According to the output result of the prestress state assessment model, a multi-level early warning module is triggered to generate an early warning signal corresponding to the output result.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the wind power steel-concrete tower prestressed intelligent monitoring system according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the wind power steel-concrete tower prestressed intelligent monitoring system according to any one of claims 1 to 8 are implemented.

Images