A fan bolt monitoring method based on ultrasonic and acoustic emission technology

Abstract

This invention relates to a method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technologies, belonging to the field of bolt monitoring technology. The method involves acquiring the raw acoustic emission signal from the monitoring point of the wind turbine bolt; comparing the signal amplitude with a dynamic threshold customized for that monitoring point to determine whether an abnormal impact event has occurred; if so, extracting the signal characteristic parameters of the event; analyzing the characteristic parameters according to preset defect characteristic rules to determine the defect type as macroscopic damage, friction or fretting, or unknown type; and executing differentiated response strategies based on the defect type, including direct early warning for macroscopic damage, triggering ultrasonic measurement for friction or fretting events to accurately quantify the current preload and determine whether it is abnormal, and generating verification instructions for unknown types. This application, through the synergy of acoustic emission and ultrasonic technologies, integrates early dynamic damage event capture with accurate static preload measurement, achieving real-time, comprehensive, and accurate monitoring and early warning of the health status of wind turbine bolts.

Description

Technical Field

[0001] This invention relates to the field of bolt monitoring technology, and in particular to a method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technologies. Background Technology

[0002] As large rotating equipment, wind turbine generators rely on thousands of high-strength bolts to connect critical structural components such as the tower, nacelle, and blades. Over an operational cycle of more than twenty years, these bolts continuously endure enormous alternating loads, strong wind-induced vibrations, and the corrosive effects of extreme temperature and humidity conditions. Their preload and structural integrity directly affect the safe and stable operation of the entire unit. Loosening of bolts or the development of fatigue cracks can lead to connection failure, component displacement, and even catastrophic accidents such as tower overturning.

[0003] Currently, widely used traditional technical solutions mainly include torque-based monitoring methods, mechanical sensor-based monitoring methods, and vibration characteristic-based monitoring methods.

[0004] However, torque-based monitoring methods suffer from low accuracy, are greatly affected by the coefficient of friction, causing significant errors in preload, and cannot be monitored in real time. Mechanical sensor-based methods require long-term operation under harsh conditions, posing challenges to the reliability of the sensor's packaging, the durability of its leads and connectors, and making them prone to failure. Furthermore, deploying a large number of sensors on a single wind turbine for comprehensive monitoring is extremely costly in terms of installation and hardware. Vibration-based monitoring methods are not effective at identifying early defects and struggle to locate the bolts containing defects.

[0005] Therefore, there is an urgent need for a wind turbine bolt monitoring solution based on ultrasonic and acoustic emission technologies that can provide timely and accurate feedback on the operating status of wind turbine bolts. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide a method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technologies, aiming to solve at least one of the above-mentioned technical problems.

[0007] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: Firstly, this application provides a method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technologies, employing the following technical solution: A method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technologies includes: Acquire the raw acoustic emission signal from the fan bolt monitoring point; Based on the amplitude of the original acoustic emission signal and the dynamic threshold corresponding to the wind turbine bolt monitoring point, the monitoring result of the wind turbine bolt monitoring point is determined. The monitoring result includes the occurrence of an abnormal impact event and the absence of an abnormal impact event. The dynamic threshold is determined based on the attenuation curve of the acoustic emission signal corresponding to the wind turbine bolt monitoring point and the distance between the acoustic emission sensor and the monitoring point. If the monitoring result indicates that an abnormal impact event has occurred, then the signal feature parameters of the abnormal impact event are extracted; Based on the signal characteristic parameters and preset defect characteristic rules, the defect type corresponding to the abnormal impact event is determined; Based on the defect type of the wind turbine bolt monitoring point, a target response strategy is determined, and the corresponding operation is executed according to the target response strategy. The target response strategy is a first response strategy, a second response strategy, or a third response strategy. The first response strategy represents the response strategy corresponding to the defect type being a macroscopic damage event. The second response strategy represents the response strategy corresponding to the defect type being a friction or micro-motion event. The third response strategy represents the response strategy corresponding to the defect type being an unknown type event.

[0008] The beneficial effects of this invention are as follows: Utilizing the high sensitivity of acoustic emission technology to early defects, when the acoustic emission technology captures an abnormal impact signal, it can immediately trigger or enhance a differentiated response strategy for the bolt at that location, thereby simultaneously obtaining "event alarms" and "quantitative data," providing the most comprehensive information support for operation and maintenance decisions, and realizing full-dimensional monitoring of the bolt's health status from "dynamic damage" to "static force value." By classifying acoustic emission signals (macroscopic damage, friction micro-motion, unknown type) through preset defect characteristic rules and driving differentiated response strategies, intelligent and precise monitoring is achieved.

[0009] Based on the above technical solution, the present invention can be further improved as follows.

[0010] Furthermore, determining the monitoring result of the wind turbine bolt monitoring point based on the amplitude of the original acoustic emission signal and the dynamic threshold corresponding to the wind turbine bolt monitoring point includes: Obtain the bolt information of the wind turbine bolt monitoring point, where each wind turbine bolt monitoring point corresponds to one bolt, and the bolt information includes bolt number, location, specifications, and temperature; Based on the bolt information of the wind turbine bolt monitoring points and the pre-established standard bolt model library, the acoustic emission signal attenuation curve corresponding to the wind turbine bolt monitoring points and the distance between the acoustic emission sensor and the monitoring points are determined. The dynamic threshold is determined based on the acoustic emission signal attenuation curve corresponding to the wind turbine bolt monitoring point and the distance between the acoustic emission sensor and the monitoring point; Based on the amplitude of the original acoustic emission signal and the dynamic threshold corresponding to the wind turbine bolt monitoring point, it is determined whether an abnormal impact event has occurred at the wind turbine bolt monitoring point. If the amplitude of the original acoustic emission signal is greater than the dynamic threshold corresponding to the wind turbine bolt monitoring point, then it is determined that an abnormal impact event has occurred at the wind turbine bolt monitoring point. If the amplitude of the original acoustic emission signal is not greater than the dynamic threshold corresponding to the wind turbine bolt monitoring point, then it is determined that no abnormal impact event has occurred at the wind turbine bolt monitoring point.

[0011] The beneficial effects of adopting the above-mentioned further scheme are as follows: Based on the specific specifications and location information of each bolt, as well as the pre-built acoustic emission signal attenuation curve, a dynamic threshold specific to the wind turbine bolt monitoring point is calculated in real time. This fully considers the distance attenuation characteristics of the acoustic emission signal propagating in the bolt and connection structure, ensuring that the threshold setting is precisely matched with the actual installation position of the sensor and the geometry of the bolt. This improves the sensitivity and accuracy of monitoring, effectively capturing early, weak damage signals from critical areas such as the bolt root. Simultaneously, by comparing the amplitude of the real-time acquired acoustic emission signal with this dynamic threshold to determine abnormal events, an adaptive and interference-resistant intelligent triggering mechanism is constructed.

[0012] Furthermore, before acquiring the raw acoustic emission signal from the wind turbine bolt monitoring point, the process also includes: Establish a standard bolt model library corresponding to the bolts at each wind turbine bolt monitoring point. The standard bolt model library includes axial stress-acoustic time difference calibration curves and acoustic emission signal attenuation curves for different wind turbine bolt specifications. The establishment of a standard bolt model library corresponding to the bolts at each wind turbine bolt monitoring point includes: For each bolt, the ultrasonic propagation time and initial ultrasonic propagation time of the bolt under known axial loads at various levels are obtained, wherein the initial ultrasonic propagation time characterizes the ultrasonic propagation time of the bolt in a free state. For each bolt, the acoustic transit time under each loading level is calculated based on the ultrasonic propagation time under each known axial load and the initial ultrasonic propagation time. For each bolt, based on the acoustic transit time under each loading level, an axial stress-acoustic transit time calibration curve is established through linear regression analysis; and, For each bolt, the amplitude of the acoustic emission signal excited by the Hsu-Nielsen source at test points at different known distances and received by a fixed acoustic emission sensor is obtained; For each bolt, the acoustic emission signal attenuation curve is generated by fitting the data based on the relationship between distance and amplitude data pairs from multiple test points.

[0013] The beneficial effects of adopting the above-mentioned further scheme are as follows: By conducting graded loading tests on sample bolts, the correspondence between axial stress and ultrasonic transit time is accurately obtained, and a high-precision calibration curve is generated through linear regression analysis; in the simulated installation structure, a standard fracture source is used to excite at a series of known distances to obtain the attenuation law of the acoustic emission signal on a specific propagation path, and an attenuation curve is generated by fitting. The modeling method based on measured data ensures that the established model library has extremely high accuracy, repeatability, and reliability.

[0014] Furthermore, the signal characteristic parameters include signal amplitude, signal energy, signal count, and signal duration. The step of determining the defect type corresponding to the abnormal impact event based on the signal characteristic parameters and preset defect characteristic rules includes: If the signal amplitude is greater than a preset amplitude threshold, the signal energy is greater than a preset energy threshold, and the signal duration is greater than a preset duration threshold, then the defect type corresponding to the abnormal impact event is determined to be a macroscopic damage event. If the signal amplitude is not greater than a preset amplitude threshold and the signal count per unit time is greater than a preset count threshold, then the defect type corresponding to the abnormal impact event is determined to be a friction or micro-motion event. If the abnormal impact event is not a macroscopic damage event, friction event, or micro-motion event, then the defect type corresponding to the abnormal impact event is determined to be an unknown type event.

[0015] The beneficial effects of adopting the above-mentioned further approach are: by utilizing multiple key characteristic parameters such as signal amplitude, energy, count, and duration, and by pre-setting targeted judgment rules and thresholds for them, this multi-dimensional and quantitative analysis method can effectively capture and distinguish the differences in acoustic emission signal characteristics generated by different physical mechanisms: accurately identifying high-intensity, high-energy, and long-duration signals as macroscopic damage events (such as crack propagation), while identifying low-amplitude, high-count signals as friction or micro-motion events (such as the initial stage of loosening), thus achieving accurate classification.

[0016] Furthermore, determining the target response strategy based on the defect type of the wind turbine bolt monitoring points includes: If the target response strategy is the first response strategy, then a first warning instruction is generated; If the target response strategy is the second response strategy, then ultrasonic measurement is triggered for the wind turbine bolt monitoring point to obtain the current ultrasonic propagation time of the bolt corresponding to the wind turbine bolt monitoring point; the acoustic time difference is calculated based on the current ultrasonic propagation time, and the current preload of the bolt is determined according to the axial stress-acoustic time difference calibration curve corresponding to the wind turbine bolt monitoring point. Determine whether the current preload exceeds the preset preload safety range. If the current preload exceeds the preset preload safety range, generate a second warning command. If the target response strategy is the third response strategy, then a verification instruction is generated.

[0017] The beneficial effects of adopting the above-mentioned further solutions are as follows: For high-risk events such as macroscopic damage, a high-level early warning is generated immediately, ensuring that major safety hazards can be captured and responded to in the first instance, avoiding catastrophic accidents that may be caused by process delays; for events such as friction or micro-motion, which indicate the initial stage of loosening, a targeted high-precision ultrasonic measurement is triggered. This achieves seamless connection and collaborative verification between early acoustic emission warning and ultrasonic quantitative verification. It can confirm whether loosening has actually occurred and its severity through the pre-tightening force value measured by ultrasound, reducing the false alarm rate caused by misjudgment due to a single technology, and providing accurate quantitative basis for operation and maintenance. For unknown types of events, a verification instruction is generated. Through manual verification, if normal, the signal is added to a whitelist, and similar signals will not be prompted again in the future. If abnormal, the defect results obtained from on-site detection and the characteristics of the signal are added to the database, and an early warning can be directly issued when the same signal is encountered in the future.

[0018] Furthermore, it also includes: The preliminary location result is determined based on the time difference of arrival of signals from the same abnormal impact event received by multiple acoustic emission sensors. Based on the measured signal amplitude of each of the acoustic emission sensors, the preset acoustic emission signal attenuation curve, and the preliminary positioning results, the precise location of the defect source corresponding to the abnormal impact event is determined. Based on the precise location and the acoustic emission signal attenuation curve, distance attenuation compensation is performed on the amplitude of each measured signal to determine the normalized signal intensity of the defect source. Based on the normalized signal strength, the warning level of the abnormal impact event is determined.

[0019] The beneficial effects of adopting the above-mentioned further scheme are as follows: Preliminary positioning is achieved by utilizing the time difference of arrival of signals from multiple sensors, followed by matching and verification with the measured amplitudes of each sensor and the theoretical amplitudes predicted based on the acoustic emission signal attenuation curve, thus improving the positioning accuracy of the defect location; Normalization of the measured signal amplitude using the attenuation curve eliminates the attenuation effect on signal strength caused by different sound wave propagation distances, allowing for the calculation of the source intensity reflecting the severity of the defect event itself. This enables an objective and quantitative assessment of the severity and development trend of the defect, achieving risk classification and early warning.

[0020] Furthermore, it also includes: Acquire historical preload force and acoustic emission event activity data for wind turbine bolts; Based on the historical preload, a curve of preload decay over time is fitted, and according to the curve, the time point at which the preload drops to a preset safe preload threshold is determined, and the time point is used as the preliminary prediction value of the remaining service life of the wind turbine bolt. Based on the changing trend of the acoustic emission event activity data, the preliminary prediction value of the remaining service life is corrected to obtain the corrected prediction value of the remaining service life of the wind turbine bolts.

[0021] The beneficial effects of adopting the above-mentioned further scheme are as follows: Based on the objective law of bolt preload decay with service time, curve fitting is performed to calculate the time point when the preload drops to the safe threshold, thereby obtaining the baseline prediction value of the remaining service life. The changing trend of acoustic emission event activity is introduced as a cross-validation and dynamic correction factor. This is because a sharp increase in acoustic emission activity often indicates accelerated material damage and a new stage of fatigue accumulation at the microscopic level. Even if the current preload has not exceeded the limit, this can provide timely warnings and shorten (correct) the remaining service life prediction, improving the timeliness and accuracy of the prediction and avoiding the potential lag risk associated with predictions based on a single static parameter. Secondly, this application provides a wind turbine bolt monitoring device based on ultrasonic and acoustic emission technologies, employing the following technical solution: A wind turbine bolt monitoring device using ultrasonic and acoustic emission technologies, comprising: The acquisition module is used to acquire the original acoustic emission signals from the wind turbine bolt monitoring points; The judgment module is used to determine the monitoring result of the wind turbine bolt monitoring point based on the amplitude of the original acoustic emission signal and the dynamic threshold corresponding to the wind turbine bolt monitoring point. The monitoring result includes whether an abnormal impact event has occurred or not. The dynamic threshold is determined based on the attenuation curve of the acoustic emission signal corresponding to the wind turbine bolt monitoring point and the distance between the acoustic emission sensor and the monitoring point. The feature extraction module is used to extract the signal feature parameters of the abnormal impact event if the monitoring result indicates that an abnormal impact event has occurred. The defect classification module is used to determine the defect type corresponding to the abnormal impact event based on the signal feature parameters and preset defect feature rules. The early warning module is used to determine a target response strategy based on the defect type of the wind turbine bolt monitoring point, and to perform corresponding operations according to the target response strategy. The target response strategy is a first response strategy, a second response strategy, or a third response strategy. The first response strategy represents the response strategy corresponding to the defect type being a macroscopic damage event. The second response strategy represents the response strategy corresponding to the defect type being a friction or micro-motion event. The third response strategy represents the response strategy corresponding to the defect type being an unknown type event.

[0022] Thirdly, this application provides an electronic device that adopts the following technical solution: An electronic device includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any of the first aspects, a method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technologies.

[0023] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium storing a computer program capable of being loaded by a processor and executing the wind turbine bolt monitoring method based on ultrasonic and acoustic emission technology as described in any one of the first aspects.

[0024] Additional aspects and advantages of this application will be set forth in part in the description which follows, and will become apparent from the description or may be learned by practice of this application. Attached Figure Description

[0025] Figure 1 A flowchart illustrating a method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technologies, provided as an embodiment of the present invention; Figure 2 Another schematic flowchart of a wind turbine bolt monitoring method based on ultrasonic and acoustic emission technology is provided as an embodiment of the present invention; Figure 3 This is a schematic diagram of a wind turbine bolt monitoring device based on ultrasonic and acoustic emission technology, provided in one embodiment of the present invention. Figure 4 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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 some embodiments of this application, not all 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.

[0027] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0028] This application provides a method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technologies. This method can be executed by an electronic device, which can be a server or a mobile terminal device. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The mobile terminal device can be a laptop computer, a desktop computer, etc., but is not limited to these.

[0029] like Figure 1 and Figure 2 As shown, a method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technologies mainly includes: S1, acquire the original acoustic emission signal of the fan bolt monitoring point; In this embodiment of the application, before acquiring the original acoustic emission signal of the wind turbine bolt monitoring point, the method further includes: Establish a standard bolt model library corresponding to the bolts at each wind turbine bolt monitoring point. The standard bolt model library includes axial stress-acoustic time difference calibration curves and acoustic emission signal attenuation curves for different wind turbine bolt specifications. The establishment of a standard bolt model library corresponding to the bolts at each wind turbine bolt monitoring point includes: For each bolt, the ultrasonic propagation time and initial ultrasonic propagation time of the bolt under known axial loads at various levels are obtained, wherein the initial ultrasonic propagation time characterizes the ultrasonic propagation time of the bolt in a free state. For each bolt, the acoustic transit time under each loading level is calculated based on the ultrasonic propagation time under each known axial load and the initial ultrasonic propagation time. For each bolt, based on the acoustic transit time under each loading level, an axial stress-acoustic transit time calibration curve is established through linear regression analysis; and, For each bolt, the amplitude of the acoustic emission signal excited by the Hsu-Nielsen source at test points at different known distances and received by a fixed acoustic emission sensor is obtained; For each bolt, the acoustic emission signal attenuation curve is generated by fitting the data based on the relationship between distance and amplitude data pairs from multiple test points.

[0030] In the above implementation, at least three bolts of the same specification as the bolt to be tested are selected for calibration curve plotting; the bolts are subjected to progressively applied loading at 15 equal loading levels, from 0 to 80% of the bolt's yield strength, and the actual force value F under each load is recorded. i and the current sound time t i The load is applied until the maximum design load is reached; for the same bolt, the load is applied three times; then the same bolt of the same specification is used and the process is repeated to complete the test for this type of bolt; the acoustic time difference Δt is determined from the test results.i , Δt i =t i -t0 (t0 is the free state sound time of the bolt), for (F i , Δt i Linear regression analysis was performed to establish the axial stress-acoustic time difference calibration curve.

[0031] In the above implementation, a bolt of the same specification as the bolt to be tested is selected to plot the acoustic emission signal attenuation curve; a sensor is fixed at a point on the structure, which is the actual position of the sensor during the monitoring process; with the fixed sensor position as the center, a test point is set every 50 mm along radial test lines in different directions, and a standard fracture operation (breaking at an angle of about 30 degrees to the surface) is performed using an Hsu-Nielsen source (pencil lead fracture source); the distance D from the test point (sound source) to the fixed sensor and the peak amplitude A (dB) of the event received by the fixed sensor are recorded, and each test point is excited at least 5 times and the average value is taken; the acoustic emission signal attenuation curve is plotted with distance D as the abscissa and amplitude A as the ordinate.

[0032] In this embodiment, the wind turbine bolt monitoring point refers to a specific high-strength bolt and its surrounding local structural area selected for online health status monitoring in the wind turbine generator set, such as a bolt at a critical location like the tower flange connection or blade root connection. The raw acoustic emission signal refers to the initial electrical signal or voltage-time sequence directly sensed and output by an acoustic emission sensor installed near the monitoring point, without any digital signal processing (such as filtering, amplification, or feature extraction).

[0033] During wind turbine operation, bolts may experience microscopic or macroscopic damage (such as dislocation movement, crack initiation and propagation, and friction) due to loosening, fatigue, or other reasons. Each damage event excites a high-frequency stress pulse (i.e., acoustic emission wave) in the material. This stress wave propagates to the surface through the bolt and connecting structure, causing micrometer-level surface displacement. The piezoelectric crystal in the acoustic emission sensor, located close to the bolt head or the substrate surface, senses this vibration and generates a weak analog voltage signal based on the positive piezoelectric effect. This signal is transmitted to the data acquisition system via a coaxial cable. The acquisition card performs synchronous and continuous analog-to-digital (A / D) conversion on it at an extremely high sampling rate (typically in the megahertz range), thus forming a sequence of digital voltage values ​​arranged in chronological order, i.e., the original acoustic emission signal data stream.

[0034] S2, based on the amplitude of the original acoustic emission signal and the dynamic threshold corresponding to the wind turbine bolt monitoring point, determine the monitoring result of the wind turbine bolt monitoring point. The monitoring result includes whether an abnormal impact event has occurred or not. The dynamic threshold is determined based on the attenuation curve of the acoustic emission signal corresponding to the wind turbine bolt monitoring point and the distance between the acoustic emission sensor and the monitoring point. In this embodiment of the application, determining the monitoring result of the wind turbine bolt monitoring point based on the amplitude of the original acoustic emission signal and the dynamic threshold corresponding to the wind turbine bolt monitoring point includes: Obtain the bolt information of the wind turbine bolt monitoring point, where each wind turbine bolt monitoring point corresponds to one bolt, and the bolt information includes bolt number, location, specifications, and temperature; Based on the bolt information of the wind turbine bolt monitoring points and the pre-established standard bolt model library, the acoustic emission signal attenuation curve corresponding to the wind turbine bolt monitoring points and the distance between the acoustic emission sensor and the monitoring points are determined. The dynamic threshold is determined based on the acoustic emission signal attenuation curve corresponding to the wind turbine bolt monitoring point and the distance between the acoustic emission sensor and the monitoring point; Based on the amplitude of the original acoustic emission signal and the dynamic threshold corresponding to the wind turbine bolt monitoring point, it is determined whether an abnormal impact event has occurred at the wind turbine bolt monitoring point. If the amplitude of the original acoustic emission signal is greater than the dynamic threshold corresponding to the wind turbine bolt monitoring point, then it is determined that an abnormal impact event has occurred at the wind turbine bolt monitoring point. If the amplitude of the original acoustic emission signal is not greater than the dynamic threshold corresponding to the wind turbine bolt monitoring point, then it is determined that no abnormal impact event has occurred at the wind turbine bolt monitoring point.

[0035] In the above embodiments, bolt information refers to a set of attribute data that uniquely identifies and describes the monitored bolt object, which is used to accurately represent the physical object in the digital system. The bolt number it contains represents a unique identification code compiled according to the "wind farm-wind turbine-component-location" rule, which is used to realize the digital addressing and traceability of bolts.

[0036] Location refers to the spatial coordinates or installation point of the bolt within the three-dimensional structure of the wind turbine, used to associate its sound wave propagation path; specifications refer to the bolt's model, diameter, length, material grade, strength grade, and other physical and mechanical parameters, serving as a key index for selecting the corresponding calibration model; temperature refers to the current temperature value of the bolt or its surrounding environment, collected in real time by an integrated or nearby temperature sensor, used to compensate for and correct acoustic parameters such as sound velocity. The distance between the acoustic emission sensor and the monitoring point refers to the geometric straight-line distance or equivalent sound path between the installation location of the acoustic emission sensor and the high-incidence area of ​​potential defects in the monitored bolt (such as the thread root or shank), a key parameter for calculating the signal attenuation during propagation.

[0037] S3, if the monitoring result indicates that an abnormal impact event has occurred, then extract the signal feature parameters of the abnormal impact event; In this embodiment of the application, once the step determines that an abnormal collision event has occurred, the original data segment corresponding to the event will be locked in time immediately.

[0038] The signal amplitude is calculated by iterating through all data points of the waveform segment, finding the maximum absolute value, and then summing and integrating the summations over the entire event duration. Simultaneously, a low counting threshold is set (typically higher than the background noise but much lower than the dynamic threshold for event detection), and the number of times the waveform crosses this threshold is counted to obtain the signal count. Finally, the signal duration is determined, which is the time difference from the moment the waveform first exceeds the event detection threshold (or another set duration start threshold) to the moment the waveform finally falls back and stabilizes below that threshold. All these calculated parameter values ​​are encapsulated into a feature vector.

[0039] S4. Based on the signal characteristic parameters and preset defect characteristic rules, determine the defect type corresponding to the abnormal impact event; In this embodiment of the application, the signal characteristic parameters include signal amplitude, signal energy, signal count, and signal duration. The step of determining the defect type corresponding to the abnormal impact event based on the signal characteristic parameters and preset defect characteristic rules includes: If the signal amplitude is greater than a preset amplitude threshold, the signal energy is greater than a preset energy threshold, and the signal duration is greater than a preset duration threshold, then the defect type corresponding to the abnormal impact event is determined to be a macroscopic damage event. The macroscopic damage event is a high-intensity, high-energy, long-duration event, and the signal characteristics belong to macroscopic crack propagation and plastic deformation. If the signal amplitude is not greater than the preset amplitude threshold and the signal count per unit time is greater than the preset count threshold, then the defect type corresponding to the abnormal impact event is determined to be a friction or fretting event. Friction or fretting events are low-amplitude, high-count, continuous events. This signal is related to friction, fretting wear, and leakage, and is common in the early stage of loosening. If the abnormal impact event is not a macroscopic damage event, friction event, or micro-motion event, then the defect type corresponding to the abnormal impact event is determined to be an unknown type event.

[0040] S5. Based on the defect type of the wind turbine bolt monitoring point, determine the target response strategy and execute the corresponding operation according to the target response strategy. The target response strategy is a first response strategy, a second response strategy, or a third response strategy. The first response strategy represents the response strategy corresponding to the defect type being a macroscopic damage event. The second response strategy represents the response strategy corresponding to the defect type being a friction or micro-motion event. The third response strategy represents the response strategy corresponding to the defect type being an unknown type event.

[0041] In this embodiment of the application, determining the target response strategy based on the defect type of the wind turbine bolt monitoring point includes: If the target response strategy is the first response strategy, then a first warning instruction is generated; If the target response strategy is the second response strategy, then ultrasonic measurement is triggered for the wind turbine bolt monitoring point to obtain the current ultrasonic propagation time of the bolt corresponding to the wind turbine bolt monitoring point; the acoustic time difference is calculated based on the current ultrasonic propagation time, and the current preload of the bolt is determined according to the axial stress-acoustic time difference calibration curve corresponding to the wind turbine bolt monitoring point. Determine whether the current preload exceeds the preset preload safety range. If the current preload exceeds the preset preload safety range, generate a second warning command. If the target response strategy is the third response strategy, then a verification instruction is generated.

[0042] The signal characteristics of unknown type events are not common defect signal characteristics, so on-site detection is required. If normal, the signal is added to the whitelist and similar signals will not be prompted again. If abnormal, the defect results obtained from on-site detection and the signal characteristics are added to the database, and a warning can be issued directly when the signal is encountered in the future.

[0043] As a further optional implementation method in the embodiments of this application, it also includes: The preliminary location result is determined based on the time difference of arrival of signals from the same abnormal impact event received by multiple acoustic emission sensors. Based on the measured signal amplitude of each of the acoustic emission sensors, the preset acoustic emission signal attenuation curve, and the preliminary positioning results, the precise location of the defect source corresponding to the abnormal impact event is determined. Based on the precise location and the acoustic emission signal attenuation curve, distance attenuation compensation is performed on the amplitude of each measured signal to determine the normalized signal intensity of the defect source. Based on the normalized signal strength, the warning level of the abnormal impact event is determined.

[0044] In this embodiment, the time difference of the signal arriving at different sensors is used for preliminary positioning. Then, the measured signal amplitude of each sensor is matched with the amplitude predicted based on the location and the acoustic emission signal attenuation curve in the database, thereby determining the location of the defect.

[0045] Based on the monitored acoustic emission signal intensity and the located sound source position, combined with the acoustic emission signal attenuation curves in the database, the intensity of the sound source can be determined, eliminating the influence of propagation distance and reflecting the intensity of the defect event itself. This allows for the monitoring of the severity of defect activity. If the sound source intensity shows an increasing trend over time, especially with the appearance of a high-amplitude (>80dB) sudden signal, this is a strong warning of crack propagation or impending material fracture, far more valuable for judgment than the original signal amplitude. When this occurs, the warning form changes, issuing an alarm in a more prominent manner. For example, the normalized signal intensity corresponds to a higher warning level.

[0046] As a further optional implementation method in the embodiments of this application, it also includes: Acquire historical preload force and acoustic emission event activity data for wind turbine bolts; Based on the historical preload, a curve of preload decay over time is fitted, and according to the curve, the time point at which the preload drops to a preset safe preload threshold is determined, and the time point is used as the preliminary prediction value of the remaining service life of the wind turbine bolt. Based on the changing trend of the acoustic emission event activity data, the preliminary prediction value of the remaining service life is corrected to obtain the corrected prediction value of the remaining service life of the wind turbine bolts.

[0047] In this embodiment, historical preload data sequences for a specific bolt are retrieved from a database. These data may have unequal time intervals, but all contain precise timestamps. Next, a suitable regression algorithm (such as least squares fitting to an exponential or power-law decay curve) is used to fit these data, resulting in a preload decay curve that can extrapolate future trends. Then, on this curve, the future time point corresponding to a value equal to a preset safe preload threshold is found. The time difference between the current time and this future time point is calculated as a preliminary prediction of the remaining service life.

[0048] However, relying solely on preload decay may not be able to capture sudden changes in the material's internal damage mechanism in a timely manner (such as the transition from uniform relaxation to rapid local crack propagation). Therefore, acoustic emission event activity data within the same time period are analyzed in parallel.

[0049] A sharp or accelerated increase in acoustic emission activity is a strong early warning signal that material damage accumulation has entered a new stage and the risk of failure is increasing. Therefore, if an upward trend in activity is detected, especially an accelerated increase, a risk coefficient should be generated or the preliminary prediction value should be shortened by a certain proportion.

[0050] For example, even if the current preload is adequate, a sudden increase in acoustic emission activity may indicate a shortened remaining service life. The correction algorithm can range from a simple percentage adjustment to a more complex weighted fusion based on a failure physics model. The final corrected remaining service life prediction integrates macroscopic state and microscopic activity information, resulting in higher prediction accuracy and providing crucial decision-making support for scheduling optimal maintenance.

[0051] This method leverages the high sensitivity of acoustic emission technology to early-stage defects. When acoustic emission technology detects an abnormal impact signal, it can immediately trigger or enhance a differentiated response strategy for the bolt at that location, thereby simultaneously obtaining both "event alarms" and "quantitative data." This provides comprehensive information support for operational and maintenance decisions, enabling full-dimensional monitoring of bolt health status from "dynamic damage" to "static force values." By classifying acoustic emission signals (macroscopic damage, friction micro-motion, and unknown types) using preset defect characteristic rules and driving differentiated response strategies, intelligent and precise monitoring is achieved.

[0052] Figure 3 A schematic diagram of a wind turbine bolt monitoring device 200 based on ultrasonic and acoustic emission technologies is shown.

[0053] like Figure 3 As shown, a wind turbine bolt monitoring device 200 based on ultrasonic and acoustic emission technology mainly includes: Acquisition module 201 is used to acquire the original acoustic emission signal of the wind turbine bolt monitoring point; The judgment module 202 is used to determine the monitoring result of the wind turbine bolt monitoring point based on the amplitude of the original acoustic emission signal and the dynamic threshold corresponding to the wind turbine bolt monitoring point. The monitoring result includes the occurrence of an abnormal impact event and the absence of an abnormal impact event. The dynamic threshold is determined based on the attenuation curve of the acoustic emission signal corresponding to the wind turbine bolt monitoring point and the distance between the acoustic emission sensor and the monitoring point. The feature extraction module 203 is used to extract the signal feature parameters of the abnormal impact event if the monitoring result indicates that an abnormal impact event has occurred. The defect classification module 204 is used to determine the defect type corresponding to the abnormal impact event based on the signal feature parameters and preset defect feature rules. The early warning module 205 is used to determine a target response strategy based on the defect type of the wind turbine bolt monitoring point, and to perform corresponding operations according to the target response strategy. The target response strategy is a first response strategy, a second response strategy, or a third response strategy. The first response strategy represents the response strategy corresponding to the defect type being a macroscopic damage event. The second response strategy represents the response strategy corresponding to the defect type being a friction or micro-motion event. The third response strategy represents the response strategy corresponding to the defect type being an unknown type event.

[0054] In one example, the module in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0055] For example, when modules in a device can be implemented via a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling programs. Alternatively, these modules can be integrated together as a system-on-a-chip (SOC).

[0056] In this application, various objects such as messages / information / devices / network elements / systems / apparatus / actions / operations / processes / concepts may be named. It is understood that these specific names do not constitute a limitation on the relevant objects. The names may be changed depending on the scenario, context, or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from their functions and technical effects embodied / performed in the technical solution.

[0057] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0058] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0059] Figure 4 This is a structural block diagram of an electronic device 300 according to an embodiment of this application.

[0060] like Figure 4 As shown, the electronic device 300 includes a processor 301 and a memory 302, and may further include one or more of an information input / output (I / O) interface 303, a communication component 304, and a communication bus 305.

[0061] The processor 301 controls the overall operation of the electronic device 300 to complete all or part of the steps in the aforementioned method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technologies. The memory 302 stores various types of data to support the operation of the electronic device 300. This data may include, for example, instructions for any application or method operating on the electronic device 300, as well as application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as one or more of Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0062] I / O interface 303 provides an interface between processor 301 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 304 is used to test wired or wireless communication between electronic device 300 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 304 may include a Wi-Fi component, a Bluetooth component, and an NFC component.

[0063] The communication bus 305 may include a path for transmitting information between the aforementioned components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 may be divided into an address bus, a data bus, a control bus, etc.

[0064] The electronic device 300 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the wind turbine bolt monitoring method based on ultrasonic and acoustic emission technology given in the above embodiments.

[0065] The following describes the computer-readable storage medium provided in the embodiments of this application. The computer-readable storage medium described below can be referred to in correspondence with the wind turbine bolt monitoring method based on ultrasonic and acoustic emission technology described above.

[0066] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technologies.

[0067] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0068] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0069] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. A method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technologies, characterized in that, include: Acquire the raw acoustic emission signal from the fan bolt monitoring point; Based on the amplitude of the original acoustic emission signal and the dynamic threshold corresponding to the wind turbine bolt monitoring point, the monitoring result of the wind turbine bolt monitoring point is determined. The monitoring result includes the occurrence of an abnormal impact event and the absence of an abnormal impact event. The dynamic threshold is determined based on the attenuation curve of the acoustic emission signal corresponding to the wind turbine bolt monitoring point and the distance between the acoustic emission sensor and the monitoring point. If the monitoring result indicates that an abnormal impact event has occurred, then the signal feature parameters of the abnormal impact event are extracted; Based on the signal characteristic parameters and preset defect characteristic rules, the defect type corresponding to the abnormal impact event is determined; Based on the defect type of the wind turbine bolt monitoring point, a target response strategy is determined, and the corresponding operation is executed according to the target response strategy. The target response strategy is a first response strategy, a second response strategy, or a third response strategy. The first response strategy represents the response strategy corresponding to the defect type being a macroscopic damage event. The second response strategy represents the response strategy corresponding to the defect type being a friction or micro-motion event. The third response strategy represents the response strategy corresponding to the defect type being an unknown type event.

2. The method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technology according to claim 1, characterized in that, The determination of the monitoring results of the wind turbine bolt monitoring points based on the amplitude of the original acoustic emission signal and the dynamic threshold corresponding to the wind turbine bolt monitoring point includes: Obtain the bolt information of the wind turbine bolt monitoring point, where each wind turbine bolt monitoring point corresponds to one bolt, and the bolt information includes bolt number, location, specifications, and temperature; Based on the bolt information of the wind turbine bolt monitoring points and the pre-established standard bolt model library, the acoustic emission signal attenuation curve corresponding to the wind turbine bolt monitoring points and the distance between the acoustic emission sensor and the monitoring points are determined. The dynamic threshold is determined based on the acoustic emission signal attenuation curve corresponding to the wind turbine bolt monitoring point and the distance between the acoustic emission sensor and the monitoring point; Based on the amplitude of the original acoustic emission signal and the dynamic threshold corresponding to the wind turbine bolt monitoring point, it is determined whether an abnormal impact event has occurred at the wind turbine bolt monitoring point. If the amplitude of the original acoustic emission signal is greater than the dynamic threshold corresponding to the wind turbine bolt monitoring point, then it is determined that an abnormal impact event has occurred at the wind turbine bolt monitoring point. If the amplitude of the original acoustic emission signal is not greater than the dynamic threshold corresponding to the wind turbine bolt monitoring point, then it is determined that no abnormal impact event has occurred at the wind turbine bolt monitoring point.

3. The method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technology according to claim 1, characterized in that, Before acquiring the raw acoustic emission signal from the wind turbine bolt monitoring point, the following steps are also included: Establish a standard bolt model library corresponding to the bolts at each wind turbine bolt monitoring point. The standard bolt model library includes axial stress-acoustic time difference calibration curves and acoustic emission signal attenuation curves for different wind turbine bolt specifications. The establishment of a standard bolt model library corresponding to the bolts at each wind turbine bolt monitoring point includes: For each bolt, the ultrasonic propagation time and initial ultrasonic propagation time of the bolt under known axial loads at various levels are obtained, wherein the initial ultrasonic propagation time characterizes the ultrasonic propagation time of the bolt in a free state. For each bolt, the acoustic transit time under each loading level is calculated based on the ultrasonic propagation time under each known axial load and the initial ultrasonic propagation time. For each bolt, based on the acoustic transit time under each loading level, an axial stress-acoustic transit time calibration curve is established through linear regression analysis; and, For each bolt, the amplitude of the acoustic emission signal excited by the Hsu-Nielsen source at test points at different known distances and received by a fixed acoustic emission sensor is obtained; For each bolt, the acoustic emission signal attenuation curve is generated by fitting the data based on the relationship between distance and amplitude data pairs from multiple test points.

4. The method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technology according to claim 1, characterized in that, The signal characteristic parameters include signal amplitude, signal energy, signal count, and signal duration. The determination of the defect type corresponding to the abnormal impact event based on the signal characteristic parameters and preset defect characteristic rules includes: If the signal amplitude is greater than a preset amplitude threshold, the signal energy is greater than a preset energy threshold, and the signal duration is greater than a preset duration threshold, then the defect type corresponding to the abnormal impact event is determined to be a macroscopic damage event. If the signal amplitude is not greater than a preset amplitude threshold and the signal count per unit time is greater than a preset count threshold, then the defect type corresponding to the abnormal impact event is determined to be a friction or micro-motion event. If the abnormal impact event is not a macroscopic damage event, friction event, or micro-motion event, then the defect type corresponding to the abnormal impact event is determined to be an unknown type event.

5. The method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technology according to claim 4, characterized in that, The determination of the target response strategy based on the defect type of the wind turbine bolt monitoring points includes: If the target response strategy is the first response strategy, then a first warning instruction is generated; If the target response strategy is the second response strategy, then ultrasonic measurement is triggered for the wind turbine bolt monitoring point to obtain the current ultrasonic propagation time of the bolt corresponding to the wind turbine bolt monitoring point; the acoustic time difference is calculated based on the current ultrasonic propagation time, and the current preload of the bolt is determined according to the axial stress-acoustic time difference calibration curve corresponding to the wind turbine bolt monitoring point. Determine whether the current preload exceeds the preset preload safety range. If the current preload exceeds the preset preload safety range, generate a second warning command. If the target response strategy is the third response strategy, then a verification instruction is generated.

6. The method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technology according to claim 5, characterized in that, Also includes: The preliminary location result is determined based on the time difference of arrival of signals from the same abnormal impact event received by multiple acoustic emission sensors. Based on the measured signal amplitude of each of the acoustic emission sensors, the preset acoustic emission signal attenuation curve, and the preliminary positioning results, the precise location of the defect source corresponding to the abnormal impact event is determined. Based on the precise location and the acoustic emission signal attenuation curve, distance attenuation compensation is performed on the amplitude of each measured signal to determine the normalized signal intensity of the defect source. Based on the normalized signal strength, the warning level of the abnormal impact event is determined.

7. A method for monitoring wind turbine bolts based on ultrasonic and acoustic emission technology according to claim 5, characterized in that, Also includes: Acquire historical preload force and acoustic emission event activity data for wind turbine bolts; Based on the historical preload, a curve of preload decay over time is fitted, and according to the curve, the time point at which the preload drops to a preset safe preload threshold is determined, and the time point is used as the preliminary prediction value of the remaining service life of the wind turbine bolt. Based on the changing trend of the acoustic emission event activity data, the preliminary prediction value of the remaining service life is corrected to obtain the corrected prediction value of the remaining service life of the wind turbine bolts.

8. A fan bolt monitoring device based on ultrasonic and acoustic emission technology, characterized in that, include: The acquisition module is used to acquire the original acoustic emission signals from the wind turbine bolt monitoring points; The judgment module is used to determine the monitoring result of the wind turbine bolt monitoring point based on the amplitude of the original acoustic emission signal and the dynamic threshold corresponding to the wind turbine bolt monitoring point. The monitoring result includes whether an abnormal impact event has occurred or not. The dynamic threshold is determined based on the attenuation curve of the acoustic emission signal corresponding to the wind turbine bolt monitoring point and the distance between the acoustic emission sensor and the monitoring point. The feature extraction module is used to extract the signal feature parameters of the abnormal impact event if the monitoring result indicates that an abnormal impact event has occurred. The defect classification module is used to determine the defect type corresponding to the abnormal impact event based on the signal feature parameters and preset defect feature rules. The early warning module is used to determine a target response strategy based on the defect type of the wind turbine bolt monitoring point, and to perform corresponding operations according to the target response strategy. The target response strategy is a first response strategy, a second response strategy, or a third response strategy. The first response strategy represents the response strategy corresponding to the defect type being a macroscopic damage event. The second response strategy represents the response strategy corresponding to the defect type being a friction or micro-motion event. The third response strategy represents the response strategy corresponding to the defect type being an unknown type event.

9. An electronic device, characterized in that, Includes a processor, which is coupled to a memory; The processor is configured to execute a computer program stored in the memory to cause the electronic device to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Includes a computer program or instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1-7.

Images