Wind power main shaft crack online detection method, system and equipment and storage medium

Abstract

The invention belongs to the field of nondestructive testing of wind power generation equipment, and relates to an online detection method, system and equipment for cracks of a wind power main shaft and a storage medium. Comprising the following steps: acquiring an original acoustic signal of a high-stress area in the operation process of the wind power main shaft, and preprocessing the original acoustic signal; extracting main shaft individual voiceprint features capable of representing the operation state of the wind power main shaft; comparing the voiceprint features of the spindle individual with the voiceprint features in the normal state, and calculating to obtain a voiceprint feature difference value; real-time operation parameters of the wind power main shaft are obtained, and a dynamic threshold value is set based on the real-time operation parameters; and when the voiceprint feature difference value exceeds a dynamic threshold value, determining that the wind power main shaft has a crack initiation or expansion risk, and generating graded early warning information according to the difference value between the voiceprint feature difference value and the dynamic threshold value. According to the method, differential response from potential risks to emergency faults is realized, and the accuracy and timeliness of crack detection of the wind power main shaft and the effectiveness of operation and maintenance decision are comprehensively improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of non-destructive testing of wind power generation equipment, and relates to a wind power main shaft crack online detection method, system, device and storage medium. BACKGROUND

[0002] As an important part of clean energy, the reliability and long-term stable operation of wind power equipment are crucial to ensuring energy output. As the core transmission component of wind turbine generators, wind power main shafts are prone to fatigue cracks in high stress areas due to long-term exposure to complex alternating loads and harsh environmental conditions. If not detected and addressed in a timely manner, the propagation of cracks may lead to main shaft rupture, causing serious shutdown accidents and even catastrophic structural failures, resulting in significant economic losses and safety risks.

[0003] Currently, crack detection of wind power main shafts mainly relies on traditional non-destructive testing techniques such as ultrasonic testing, magnetic powder testing or penetration testing. However, these methods usually require implementation in a shutdown state, resulting in long detection cycles, low efficiency and inability to achieve real-time monitoring in operating conditions. In addition, due to the large size and special installation location of wind power main shafts, conventional detection methods are often inconvenient to operate and have limited coverage, making it difficult to continuously and comprehensively track the status of high stress areas. SUMMARY

[0004] To solve the problems in the prior art, the present application provides a wind power main shaft crack online detection method, system, device and storage medium, which realizes accurate detection of wind power main shaft cracks.

[0005] To achieve the above-mentioned purpose, the following technical solutions are adopted: In a first aspect, the present application provides a wind power main shaft crack online detection method, comprising the following steps: Obtaining the original acoustic signal of the high stress area of the wind power main shaft during operation, and preprocessing the original acoustic signal; Extracting a main shaft individual voiceprint feature from the preprocessed acoustic signal, which can represent the operating state of the wind power main shaft; Comparing the main shaft individual voiceprint feature with the normal state voiceprint feature to calculate a voiceprint feature difference value; Obtaining real-time operating parameters of the wind power main shaft, and setting a dynamic threshold based on the real-time operating parameters; When the voiceprint feature difference value exceeds the dynamic threshold, it is determined that the wind power main shaft has a risk of crack initiation or propagation, and a graded warning information is generated according to the difference between the voiceprint feature difference value and the dynamic threshold.

[0006] Preferably, the original acoustic signals of the high stress area are obtained by a plurality of acoustic sensors, the plurality of acoustic sensors are uniformly distributed on the outside of the shell corresponding to the high stress area of the wind turbine main shaft, and the distance between adjacent acoustic sensors is controlled within 15-20 cm.

[0007] Preferably, the step of preprocessing the original acoustic signals comprises: de-noising and filtering the original acoustic signals; signal enhancement and segmentation processing of the filtered signals.

[0008] Preferably, the step of extracting the main shaft individual acoustic print features representing the operating state of the wind turbine main shaft from the preprocessed acoustic signals comprises: time domain analysis of the preprocessed acoustic signals to extract time domain characteristic parameters including root mean square value, amplitude peak value, kurtosis index; frequency domain analysis of the preprocessed acoustic signals to obtain the frequency spectrum distribution of the signals by fast Fourier transform, and extract frequency domain characteristic parameters including amplitude, center of gravity frequency, frequency variance of main frequency components; joint time-frequency domain analysis of the preprocessed acoustic signals to obtain the energy distribution characteristics of the signals in different time scales and frequency ranges by wavelet transform or empirical mode decomposition method; fusion of the time domain characteristic parameters, frequency domain characteristic parameters and time-frequency energy distribution characteristics to obtain multi-dimensional main shaft individual acoustic print features representing the operating state of the wind turbine main shaft.

[0009] Preferably, the step of obtaining real-time operating parameters of the wind turbine main shaft and setting a dynamic threshold based on the real-time operating parameters comprises: real-time acquisition of the speed, torque, power output and environmental temperature parameters of the wind turbine main shaft; establishment of a mapping relationship model between operating parameters and acoustic print feature baseline values, the baseline values being normal state acoustic print features of the wind turbine under no-fault state corresponding to the operating parameters; obtaining of the corresponding acoustic print feature dynamic baseline values by the mapping relationship model according to the current real-time operating parameters; calculation and setting of the acoustic print feature difference value dynamic threshold under the current operating condition based on the dynamic baseline values and in combination with a pre-set safety margin coefficient.

[0010] Preferably, the determination method of the normal state acoustic print feature is: acquisition of acoustic signals of the high stress area of the wind turbine main shaft when the wind turbine main shaft is in a no-fault operating state; extraction of acoustic print features from the acoustic signals; calculation of statistical distribution values of the acoustic print features under normal state, and taking the statistical distribution values as the normal state acoustic print features.

[0011] Preferably, the step of generating the graded early warning information according to the difference between the voiceprint feature difference value and the dynamic threshold value comprises: calculating the absolute difference between the voiceprint feature difference value and the dynamic threshold value ; when , generating a first-level early warning information, which contains a text prompt and an audible and light alarm, indicating that there is a potential risk of crack initiation and suggesting scheduling a planned inspection; when , generating a second-level early warning information, which enhances the intensity of the audible and light alarm and indicates that there are obvious signs of crack propagation, suggesting that the inspection priority should be raised; when , generating a third-level early warning information, which triggers a continuous high-frequency audible and light alarm and indicates that there is a significant risk of crack propagation, suggesting that the machine should be immediately shut down for detailed inspection; wherein is the first dynamic threshold value, is the second dynamic threshold value, is the third dynamic threshold value.

[0012] In a second aspect, the present application provides a wind turbine main shaft crack online detection system, comprising: a data acquisition module for acquiring original acoustic signals of high stress areas of the wind turbine main shaft during operation and pre-processing the original acoustic signals; a feature extraction module for extracting individual voiceprint features of the wind turbine main shaft that can represent the running state of the wind turbine main shaft from the pre-processed acoustic signals; a difference value calculation module for comparing the individual voiceprint features of the wind turbine main shaft with normal state voiceprint features to calculate a voiceprint feature difference value; a threshold setting module for acquiring real-time running parameters of the wind turbine main shaft and setting a dynamic threshold value based on the real-time running parameters; an early warning module for determining that the wind turbine main shaft has a crack initiation or propagation risk when the voiceprint feature difference value exceeds the dynamic threshold value, and generating graded early warning information according to the difference between the voiceprint feature difference value and the dynamic threshold value.

[0013] In a third aspect, the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the wind turbine main shaft crack online detection method when executing the computer program.

[0014] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, wherein the computer program is executable by a processor to implement the steps of the wind turbine main shaft crack online detection method.

[0015] Compared with the prior art, the present application has the following beneficial effects: By collecting acoustic signals in the high stress area and preprocessing, the signal quality is effectively guaranteed; by extracting individual voiceprint features of the main shaft, the precise characterization of the equipment running state is realized; by calculating the voiceprint feature difference value, the quantitative evaluation of the abnormal state is realized; by setting a dynamic threshold based on real-time running parameters, the recognition adaptability under different working conditions is significantly improved; finally, through the hierarchical early warning mechanism, the differentiated response from potential risks to emergency failures is realized, and the accuracy, timeliness and effectiveness of the wind power main shaft crack detection are comprehensively improved. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments, and it should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0017] Figure 1 The flow chart of the method of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical scheme in the embodiments of the present application, and obviously, the described embodiments are part of the embodiments of the present application, not all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0020] It should be noted that: similar numbers and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0021] In the description of the embodiments of the present application, it should be noted that if the terms "upper", "lower", "horizontal", "inner" and the like indicating the orientation or position relationship are based on the orientation or position relationship shown in the drawings, or the orientation or position relationship when the product of the present application is usually placed, which is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second" and the like are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0022] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly inclined. For example, "horizontal" only means that its direction is relatively more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly inclined.

[0023] In the description of the embodiments of the present application, it should be noted that unless otherwise explicitly specified and limited, if the terms "arrangement", "installation", "connection", "connection" appear, they should be understood in a broad sense, for example, they can be fixedly connected, or can be detachably connected, or integrally connected; can be mechanically connected, or can be electrically connected; can be directly connected, or can be indirectly connected through an intermediate medium; can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0024] The present application will be described in further detail below in conjunction with the drawings: The first object of the present application is to provide a wind power main shaft crack online detection method, as shown in Figure 1 The method comprises the following steps: Acquiring the original acoustic signal of the high stress area of the wind power main shaft during operation, and pre-processing the original acoustic signal; From the pre-processed acoustic signal, the individual voiceprint feature of the main shaft capable of representing the running state of the wind power main shaft is extracted; The individual voiceprint feature of the main shaft is compared with the normal state voiceprint feature, and the voiceprint feature difference value is calculated; Acquiring the real-time running parameters of the wind power main shaft, and setting a dynamic threshold value based on the real-time running parameters; When the voiceprint feature difference value exceeds the dynamic threshold value, it is determined that the wind power main shaft has a crack initiation or expansion risk, and a graded early warning information is generated according to the difference between the voiceprint feature difference value and the dynamic threshold value.

[0025] The original acoustic signal of the high stress area is obtained and preprocessed, effectively eliminating environmental noise and mechanical interference, improving the signal-to-noise ratio of the signal, and laying a reliable data foundation for subsequent feature extraction. Then, the individual acoustic print features of the main shaft are extracted from the preprocessed signal, which can accurately represent the dynamic behavior characteristics of the main shaft in operation, and enhance the sensitivity and recognition ability to micro defects. By comparing the individual acoustic print features with the reference features under normal state and calculating the difference value, the quantitative evaluation of the main shaft state change is realized, which is beneficial to the early capture of abnormal signs. Further, the threshold is dynamically set according to the real-time running parameters, which overcomes the misjudgment problem caused by the fluctuation of working conditions, and improves the adaptability and accuracy of the detection system. Finally, through the comparison of the difference value and the dynamic threshold, the graded early warning is realized, which not only can identify the risk of crack initiation or expansion in time, but also can provide differentiated early warning information according to the risk level, so as to guide the maintenance decision, realize the real-time and accurate monitoring and early warning of the wind power main shaft structure health, and improve the operation efficiency and equipment operation safety.

[0026] Among them, the original acoustic signal of the high stress area is obtained by multiple acoustic sensors, the multiple acoustic sensors are uniformly distributed on the outside of the shell corresponding to the high stress area of the wind power main shaft, and the distance between adjacent acoustic sensors is controlled within 15-20 cm. Through the cooperative collection of multiple sensors, the system can comprehensively cover the high stress area, effectively avoid the monitoring blind area, and realize the stereoscopic capture of the crack acoustic signal. The uniform and dense distribution strategy not only enhances the sensitivity to weak early crack signals, but also can exclude local interference through signal cross verification, reducing the risk of false negatives and false positives.

[0027] For example, the steps of pre-processing the original acoustic signal include: The original acoustic signal is denoised and filtered to suppress environmental noise, electromagnetic interference and other irrelevant mechanical vibration generated high frequency or low frequency clutter; The filtered signal is enhanced and segmented, focusing on the acoustic emission events or structural vibration modes that may be related to crack generation and expansion, and the continuous signal is reasonably divided according to time or event type.

[0028] Through denoising and filtering, the signal-to-noise ratio of the signal is effectively improved, providing clean and reliable data foundation for subsequent analysis, reducing the risk of misjudgment caused by noise; signal enhancement processing amplifies the weak early crack features, improves the perception sensitivity of the system to potential risks, and is beneficial to the early detection of cracks; and the segmented processing makes the non-stationary continuous acoustic signal into a series of independent analysis segments, which not only greatly improves the efficiency and pertinence of feature calculation, but also helps to associate with specific operating state or event, further enhancing the accuracy of crack identification and state judgment.

[0029] Exemplarily, the step of extracting the main shaft individual voiceprint feature capable of representing the running state of the wind power main shaft from the pre-processed acoustic signal comprises: Performing time domain analysis on the pre-processed acoustic signal to extract time domain characteristic parameters including a root mean square value (reflecting the average energy of the signal), an amplitude peak value (capturing transient impact components), and a kurtosis index (sensitive to signal pulse abnormality), to preliminarily judge whether there is an abnormal impact or energy change; Performing frequency domain analysis on the pre-processed acoustic signal, decomposing it into a frequency spectrum by using fast Fourier transform, and extracting frequency domain characteristic parameters such as amplitude of main frequency components, center of gravity frequency (representing the position of the main component of the frequency spectrum), and frequency variance (describing the dispersion degree of the frequency spectrum), to identify the change of frequency components or the shift of resonance characteristics caused by structural cracks; Performing joint time-frequency domain analysis on the pre-processed acoustic signal, capturing local details in non-stationary signals by using wavelet transform or empirical mode decomposition, revealing the energy distribution dynamics of the signal in different time scales and frequency ranges, and effectively separating background vibration from crack-related weak transient events; Fusing the time domain characteristic parameters, the frequency domain characteristic parameters, and the time-frequency energy distribution characteristics to obtain multi-dimensional main shaft individual voiceprint features for representing the running state of the wind power main shaft.

[0030] The multi-domain joint analysis takes into account both the global statistical characteristics and the local transient information of the signal, overcomes the limitations of single domain analysis, and greatly improves the representativeness and completeness of the feature expression; the time domain parameters are sensitive to sudden abnormalities, the frequency domain parameters are good at revealing changes in structural characteristics, and the time-frequency analysis is good at capturing non-stationary crack propagation signals, and the three parameters work together to ensure that both early micro-crack initiation and slow crack propagation process can be effectively perceived Exemplarily, the step of obtaining real-time running parameters of the wind power main shaft and setting a dynamic threshold based on the real-time running parameters comprises: Real-time acquisition of the rotation speed, torque, power output, and environmental temperature parameters of the wind power main shaft; Establishing a mapping relationship model of the running parameters and the voiceprint feature baseline value, the baseline value being the normal state voiceprint feature of the wind turbine under the corresponding running parameters in the fault-free state; According to the current real-time running parameters, the corresponding voiceprint feature dynamic baseline value is obtained through the mapping relationship model; Based on the dynamic baseline value, combined with a pre-set safety margin coefficient, the voiceprint feature difference value dynamic threshold under the current working condition is calculated and set.

[0031] This dynamic threshold setting method senses key operating parameters such as speed, torque, power, and temperature in real time and establishes a precise mapping relationship between them and the characteristics of fault-free acoustic signatures, enabling the threshold to adaptively adjust according to changes in operating conditions. This mechanism effectively overcomes the problem of poor adaptability of traditional fixed thresholds under varying operating conditions, significantly reducing false alarms caused by changes in load, speed, or environment; at the same time, it automatically improves monitoring sensitivity under harsh operating conditions, avoiding the risk of missed alarms, thus achieving more reliable and accurate crack risk identification and early warning in complex operating environments.

[0032] An exemplary method for determining voiceprint features in a normal state is as follows: When the wind turbine main shaft is in a fault-free operating state, acoustic signals from its high-stress areas are collected; acoustic signature features are extracted from the acoustic signals; and the statistical distribution value of the acoustic signature features under normal conditions is calculated, which is then used as the acoustic signature features under normal conditions. This invention, by collecting acoustic signals under fault-free conditions and calculating the statistical distribution value of its acoustic signature features, can accurately and stably establish an acoustic benchmark for the health status of the main shaft. For example, the steps of generating graded early warning information based on the difference between voiceprint feature differences and dynamic thresholds include: Calculate the absolute difference between the voiceprint feature difference value and the dynamic threshold. ; when When the time comes, a Level 1 warning message will be generated, which includes text prompts and audio-visual alerts, indicating that there is a potential risk of crack initiation and recommending that a planned inspection be arranged; when When the crack is exposed, a secondary warning message is generated. This warning message enhances the intensity of the audio-visual reminder and indicates that there are obvious signs of crack expansion, suggesting that the inspection priority be increased. when At that time, a level three early warning message is generated, which triggers a continuous high-frequency audible and visual alarm and indicates that there is a significant risk of crack propagation, and recommends that the machine be stopped immediately for detailed inspection; in, The first dynamic threshold, The second dynamic threshold, This is the third dynamic threshold.

[0033] By comparing the differences in acoustic signature features with multiple dynamic thresholds and automatically triggering different levels of early warning responses based on the degree of exceedance, refined monitoring of the entire process of crack risk, from early budding to severe expansion, is achieved. This progressively enhanced alarm strategy not only significantly improves the targeting and efficiency of operation and maintenance responses but also helps to rationally allocate maintenance resources, ensuring the safe operation of wind turbines while minimizing power generation losses caused by unnecessary shutdowns.

[0034] The second object of the application is to provide a wind power main shaft crack online detection system, comprising: A data acquisition module is configured to acquire original acoustic signals of a high stress area of the wind power main shaft during operation of the wind power main shaft, and to pre-process the original acoustic signals. A feature extraction module is configured to extract a main shaft individual voiceprint feature capable of representing a running state of the wind power main shaft from the pre-processed acoustic signals. A difference value calculation module is configured to compare the main shaft individual voiceprint feature with a normal state voiceprint feature, and to calculate a voiceprint feature difference value. A threshold setting module is configured to acquire real-time running parameters of the wind power main shaft, and to set a dynamic threshold based on the real-time running parameters. An early warning module is configured to determine that the wind power main shaft has a crack initiation or expansion risk when the voiceprint feature difference value exceeds the dynamic threshold, and to generate a graded early warning information according to a difference value between the voiceprint feature difference value and the dynamic threshold.

[0035] The data acquisition module provides high-quality acoustic data basis for analysis; the feature extraction module accurately constructs the main shaft voiceprint fingerprint; the difference value calculation module realizes state quantitative evaluation; the threshold setting module ensures that the judgment standard is dynamically optimized with the working condition, effectively avoiding false positives and false negatives; and the graded early warning module ensures that different risk levels correspond to differentiated operation and maintenance responses. The modules of the system work together to improve the sensitivity of early crack identification, the reliability of monitoring results, and the intelligent level of operation and maintenance decisions, and provide key technical support for realizing predictive maintenance of wind turbines.

[0036] In an embodiment, the application provides a computer device, which comprises a processor and a memory, the memory is used to store a computer program, the computer program comprises program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in the computer storage medium to realize the corresponding method flow or corresponding function. The processor of the embodiment of the application can be used for the operation of the wind power main shaft crack online detection method.

[0037] The application further provides a storage medium, specifically a computer readable storage medium (Memory). The computer readable storage medium is a memory device in a computer device, and is used for storing programs and data. It can be understood that the computer readable storage medium herein can include an internal storage medium in the computer device, and of course can include an extended storage medium supported by the computer device. The computer readable storage medium provides a storage space, and the storage space stores an operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and the instructions can be one or more computer programs (including program codes). It should be noted that the computer readable storage medium herein can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory. One or more instructions stored in the computer readable storage medium can be loaded and executed by the processor to realize the corresponding steps of the wind power main shaft crack online detection method in the above embodiments.

[0038] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0039] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device that implements the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that carries out the function specified in the flow or flows and / or block or blocks.

[0040] These computer program instructions can also be stored in a computer readable memory capable of directing the computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce a product including instruction apparatus, which implements the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1the function specified in the one or more blocks.

[0041] These computer program instructions can also be loaded into computer or other programmable data processing devices, so that a series of operation steps are performed on the computer or other programmable data processing devices to generate computer-implemented processes, so that the instructions executed on the computer or other programmable devices provide processes for implementing the flow Figure 1 one or more flows and / or blocks Figure 1 the steps of the function specified in the one or more blocks.

[0042] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, but not to limit it, although the above embodiments of the present application have been described in detail, those skilled in the art should understand: the specific embodiments of the present application can be modified or replaced by the same, without departing from the spirit and scope of the present application, any modification or equivalent replacement, which should be covered in the protection scope of the claims of the present application.

Claims

1. A method for online detection of cracks in wind turbine main shafts, characterized in that, Includes the following steps: Acquire the original acoustic signal of the high-stress zone of the wind turbine main shaft during operation, and preprocess the original acoustic signal; Extract individual acoustic signature features of the wind turbine main shaft that can characterize its operating state from the preprocessed acoustic signal; The voiceprint features of the main axis individual are compared with the voiceprint features of the normal state, and the voiceprint feature difference value is calculated. Obtain the real-time operating parameters of the wind turbine main shaft, and set dynamic thresholds based on these real-time operating parameters; When the difference value of the acoustic signature exceeds the dynamic threshold, it is determined that there is a risk of crack initiation or propagation in the wind turbine main shaft, and a graded early warning information is generated based on the difference between the acoustic signature difference value and the dynamic threshold.

2. The online detection method for wind turbine main shaft cracks according to claim 1, characterized in that, The original acoustic signal of the high-stress zone is obtained through multiple acoustic sensors. These acoustic sensors are evenly distributed on the outer side of the shell corresponding to the high-stress zone of the wind turbine main shaft, and the distance between adjacent acoustic sensors is controlled at 15~20cm.

3. The online detection method for wind turbine main shaft cracks according to claim 1, characterized in that, The preprocessing steps for the raw acoustic signal include: The original acoustic signal is subjected to noise reduction and filtering. The filtered signal is then subjected to signal enhancement and segmentation.

4. The online detection method for wind turbine main shaft cracks according to claim 1, characterized in that, The steps for extracting individual acoustic signature features of the wind turbine main shaft from the preprocessed acoustic signal to characterize its operating state include: Time-domain analysis was performed on the preprocessed acoustic signal to extract time-domain feature parameters, including root mean square value, peak amplitude, and kurtosis index. Frequency domain analysis is performed on the preprocessed acoustic signal. The spectral distribution of the signal is obtained by fast Fourier transform, and frequency domain characteristic parameters, including the amplitude, centroid frequency, and frequency variance of the main frequency components, are extracted. The preprocessed acoustic signal is subjected to joint time-frequency domain analysis. Wavelet transform or empirical mode decomposition method is used to obtain the energy distribution characteristics of the signal in different time scales and frequency ranges. By integrating the time-domain feature parameters, frequency-domain feature parameters, and time-frequency-domain energy distribution features, a multi-dimensional individual acoustic signature feature of the wind turbine main shaft is obtained to characterize the operating state of the main shaft.

5. The online detection method for wind turbine main shaft cracks according to claim 1, characterized in that, The step of acquiring the real-time operating parameters of the wind turbine main shaft and setting a dynamic threshold based on the real-time operating parameters includes: Real-time data collection of wind turbine main shaft speed, torque, power output, and ambient temperature parameters; Establish a mapping relationship model between operating parameters and baseline values ​​of acoustic signature features, wherein the baseline values ​​are the acoustic signature features of the fan in normal state when the fan is in a fault-free state under the corresponding operating parameters; Based on the current real-time operating parameters, the corresponding dynamic baseline value of the voiceprint feature is obtained through the mapping relationship model; Based on the dynamic baseline value and combined with the preset safety margin coefficient, the dynamic threshold of the voiceprint feature difference value under the current working condition is calculated and set.

6. The online detection method for wind turbine main shaft cracks according to claim 5, characterized in that, The method for determining the voiceprint features in the normal state is as follows: When the wind turbine main shaft is in a fault-free operating state, acoustic signals from its high-stress area are collected; acoustic signature features are extracted from the acoustic signals. Calculate the statistical distribution value of the voiceprint feature under normal conditions, and use the statistical distribution value as the voiceprint feature under normal conditions.

7. The online detection method for wind turbine main shaft cracks according to claim 1, characterized in that, The steps for generating graded early warning information based on the difference between the voiceprint feature difference value and the dynamic threshold include: Calculate the absolute difference between the voiceprint feature difference value and the dynamic threshold. ; when When the time comes, a Level 1 warning message will be generated, which includes text prompts and audio-visual alerts, indicating that there is a potential risk of crack initiation and recommending that a planned inspection be arranged; when When the crack is exposed, a secondary warning message is generated. This warning message enhances the intensity of the audio-visual reminder and indicates that there are obvious signs of crack expansion, suggesting that the inspection priority be increased. when At that time, a level three early warning message is generated, which triggers a continuous high-frequency audible and visual alarm and indicates that there is a significant risk of crack propagation, and recommends that the machine be stopped immediately for detailed inspection; in, The first dynamic threshold, The second dynamic threshold, This is the third dynamic threshold.

8. An online detection system for cracks in wind turbine main shafts, characterized in that, include: Data acquisition module: used to acquire the original acoustic signals of the high-stress zone of the wind turbine main shaft during operation, and to preprocess the original acoustic signals; Characterization Extraction Module: Used to extract individual acoustic signature features of the wind turbine main shaft from the preprocessed acoustic signal, which can characterize the operating state of the main shaft. Difference value calculation module: used to compare the individual voiceprint features of the main axis with the voiceprint features of the normal state, and calculate the voiceprint feature difference value; Threshold setting module: used to acquire real-time operating parameters of the wind turbine main shaft and set dynamic thresholds based on these real-time operating parameters; Early warning module: When the difference value of the acoustic feature exceeds the dynamic threshold, it determines that there is a risk of crack initiation or expansion in the wind turbine main shaft, and generates graded early warning information based on the difference between the acoustic feature difference value and the dynamic threshold.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-7.

Images