A hardware state exception alarm monitoring method, device and equipment of a blade root load measurement system and a medium

Abstract

This application provides a hardware status anomaly alarm monitoring method, device, equipment, and medium for a blade root load measurement system, belonging to the field of wind power control technology. The method involves: real-time acquisition of the raw wavelength signal output from an optical fiber sensor, transmitting the raw wavelength signal to a fiber Bragg grating demodulator for demodulation to generate a demodulated wavelength signal and load data electrical signal; synchronous acquisition of the fiber Bragg grating demodulator parameters; performing time-series analysis on the raw wavelength signal; setting the parameter threshold range of the fiber Bragg grating demodulator and calculating the deviation between the demodulated wavelength signal and a preset standard wavelength; and executing graded early warning based on the time-series analysis results of the raw wavelength signal, the relationship between the raw wavelength signal and the demodulated wavelength signal, and the relationship between the fiber Bragg grating demodulator parameters and the parameter threshold range. This invention achieves graded early warning and intelligent diagnosis, improving the operational stability of wind turbine generators, reducing equipment downtime risks, optimizing maintenance processes, and reducing maintenance costs.

Description

Technical Field

[0001] This application belongs to the field of wind power control technology, specifically relating to a hardware status abnormality alarm monitoring method, device, equipment and medium for a blade root load measurement system. Background Technology

[0002] As the core equipment in wind power generation, the safety and reliability of wind turbine generators directly affect power generation efficiency and economic benefits. Blades are one of the most important components of a wind turbine generator, and their performance and condition have a crucial impact on the operation of the entire system. Therefore, accurately monitoring the load and vibration of the blades is key to ensuring the safe operation of wind turbine generators.

[0003] Traditional methods for monitoring blade loads primarily rely on resistance strain gauges and mechanical sensors. However, these sensors may experience performance degradation, signal attenuation, or malfunction under harsh environments such as high temperatures, humidity, and vibration, thus affecting measurement accuracy and system reliability. Furthermore, traditional sensors are often susceptible to electromagnetic interference, leading to data acquisition instability, which poses a safety hazard to wind turbine generators.

[0004] Fiber optic sensors, as an emerging monitoring application, are used in conjunction with fiber Bragg grating demodulators for sensor data acquisition. Due to their advantages such as resistance to electromagnetic interference, high sensitivity, and good corrosion resistance, they are increasingly being applied in the wind power generation field. Fiber optic sensors are responsible for real-time acquisition of physical data such as blade load and vibration, converting this data into corresponding optical signals. Utilizing the characteristics of fiber optic transmission, these optical signals are stably transmitted to the fiber Bragg grating demodulator. The fiber Bragg grating demodulator establishes a correlation between the wavelength changes of the received optical signal and changes in external physical quantities such as strain and temperature, demodulating the optical signal to accurately reconstruct the data acquired by the fiber optic sensor, thus achieving precise measurement of blade load and vibration. However, current fiber optic sensor systems suffer from insufficient hardware status monitoring. In practical applications, the status of the fiber Bragg grating demodulator and fiber optic sensors, such as wavelength, temperature, and power supply voltage, is not monitored in real time. This leads to difficulty in rapid response when faults occur, potentially causing equipment downtime or safety accidents. Furthermore, the system fails to distinguish between abnormal original wavelengths of the sensor (abnormal blade strain or sensor damage) and abnormal output of the demodulator (demodulation errors caused by hardware failure), leading to misjudgments. Summary of the Invention

[0005] In a first aspect, embodiments of this application provide a hardware status anomaly alarm monitoring method for a leaf root load measurement system, comprising the following steps:

[0006] S1. Real-time acquisition of the raw wavelength signal output from the fiber optic sensor of the leaf root load measurement system. and the original wavelength signal The signal is transmitted to a fiber Bragg grating demodulator for demodulation, generating a demodulated wavelength signal. and load data electrical signals;

[0007] S2. Parameters of the fiber optic grating demodulator for the synchronous acquisition of leaf root load measurement system: operating temperature and power supply voltage ;

[0008] S3. For the original wavelength signal Execution timing analysis:

[0009] Calculate the original wavelength signal within the set time window. mean and mean square deviation ;

[0010] Predict wavelength signal sequences over the next k periods using an autoregressive model;

[0011] The failure probability is determined using a support vector machine classification algorithm based on the predicted wavelength signal sequence. predict;

[0012] S4. Set the parameter threshold range for the fiber Bragg grating demodulator and calculate the demodulated wavelength signal. With preset standard wavelength Deviation;

[0013] S5. Based on the original wavelength signal The time-series analysis results show the original wavelength signal. With demodulated wavelength signal The relationship between the parameters of the fiber Bragg grating demodulator and the threshold range of the parameters is used to implement graded early warning.

[0014] Furthermore, the specific steps of step S2 are as follows:

[0015] S21. Obtain the operating temperature of the fiber Bragg grating demodulator using the built-in temperature sensor. ;

[0016] S22. The power supply voltage is acquired by connecting a voltage sensor in parallel at the power input terminal of the fiber Bragg grating demodulator, and the acquired analog voltage is converted into a digital signal by an analog-to-digital converter. The digital value of the power supply voltage is then read according to a preset sampling frequency.

[0017] Furthermore, the specific steps of step S3 are as follows:

[0018] S31. Calculate the original wavelength signal within the set time window. mean :

[0019]

[0020] Where n is the number of sampling points of the original wavelength signal within the time window. It is the original wavelength signal of the i-th sampling point within the time window;

[0021] S32. Calculate the original wavelength signal within the set time window. mean square deviation :

[0022] ;

[0023] S33. Predict the wavelength sequence for the next k periods using the following autoregressive model:

[0024]

[0025] in, It is the order of the autoregressive model. It is the original wavelength signal at time t. It is a constant term. It is the autoregressive coefficient. It is a white noise error term. It is the original wavelength signal at time tj, that is, the wavelength value at the j-th time point before time t;

[0026] S34. Pre-build a training dataset and train the SVM classification model;

[0027] S35. Transform the predicted wavelength signal sequence for the next k periods into a feature vector. and the feature vector Input the trained SVM classification model to obtain the decision result; the feature vector This includes statistical features extracted from wavelength signal sequences;

[0028] S36. The failure probability will be calculated based on the decision results. .

[0029] Furthermore, the timing analysis in step S3 employs a sliding window update:

[0030] Each new original wavelength signal Data points: Remove the oldest data point within the window and recalculate the original wavelength signal. mean and mean square deviation :

[0031]

[0032]

[0033] in, These are newly added raw wavelength signal data points. It is the oldest original wavelength signal data point within the time window. It is the number of sampling points of the original wavelength signal within the time window. This is the mean before the update. This is the updated mean. It is the mean squared error before the update. This is the updated mean squared error.

[0034] Furthermore, the specific steps of step S4 are as follows:

[0035] S41. Set the normal operating range of the fiber Bragg grating demodulator parameters:

[0036] Operating temperature Normal working range ;

[0037] Power supply voltage Normal working range ;

[0038] Output wavelength Normal working range ;

[0039] S42. According to the inward contraction margin Set the correction range for the parameters of the fiber Bragg grating demodulator:

[0040] Operating temperature Scope of revision work ;

[0041] Power supply voltage Scope of revision work ;

[0042] Output wavelength Correction range ;

[0043] S43. Calculate the demodulated wavelength signal With preset standard wavelength deviation ;

[0044] .

[0045] Furthermore, the inward contraction margin in step S42 Adaptive adjustment based on the historical operating conditions of the fiber Bragg grating demodulator:

[0046]

[0047] in, The historical standard deviation of the parameter, This is for the safety factor.

[0048] Furthermore, the triggering conditions for the graded early warning in step S5 are as follows:

[0049] If the demodulated wavelength signal Compared with the original wavelength signal If the difference exceeds the set deviation and the duration exceeds the set time period, a hardware fault alarm for the fiber Bragg grating demodulator will be triggered.

[0050] If the predicted fault probability of the wavelength signal sequence Greater than the preset probability threshold Or set the original wavelength signal within the time window. mean square deviation Greater than the preset mean squared error threshold This triggers an abnormal alarm from the fiber optic sensor.

[0051] If the operating temperature of the fiber Bragg grating demodulator Power supply voltage and output wavelength If at least one of the following is outside the normal operating range, a severe alarm will be triggered on the fiber Bragg grating demodulator and the machine will be shut down.

[0052] If the operating temperature of the fiber Bragg grating demodulator Power supply voltage and output wavelength All are within the normal operating range, but if at least one exceeds the correction range, a minor alarm will be triggered on the fiber Bragg grating demodulator.

[0053] If the demodulated wavelength signal With preset standard wavelength deviation Greater than the preset deviation threshold If this occurs, it will trigger an accuracy alarm in the fiber Bragg grating demodulator.

[0054] Secondly, embodiments of this application also provide a hardware status anomaly alarm monitoring device for a blade root load measurement system, comprising:

[0055] The demodulation and signal acquisition module is used to acquire the raw wavelength signal output by the fiber optic sensor of the leaf root load measurement system in real time. and the original wavelength signal The signal is transmitted to a fiber Bragg grating demodulator for demodulation, generating a demodulated wavelength signal. and load data electrical signals;

[0056] The demodulator parameter acquisition module is used to synchronously acquire parameters of the fiber optic grating demodulator in the leaf root load measurement system, including operating temperature. and power supply voltage ;

[0057] The timing analysis module is used to analyze the original wavelength signal. Execution timing analysis:

[0058] Calculate the original wavelength signal within the set time window. mean and mean square deviation ;

[0059] Predict wavelength signal sequences over the next k periods using an autoregressive model;

[0060] The failure probability is determined using a support vector machine classification algorithm based on the predicted wavelength signal sequence. predict;

[0061] The parameter threshold setting module is used to set the parameter threshold range of the fiber Bragg grating demodulator and calculate the demodulated wavelength signal. With preset standard wavelength Deviation;

[0062] The status warning module is used to monitor the original wavelength signal. The time-series analysis results show the original wavelength signal. With demodulated wavelength signal The relationship between the parameters of the fiber Bragg grating demodulator and the threshold range of the parameters is used to implement graded early warning.

[0063] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the hardware status abnormality alarm monitoring method of the leaf root load measurement system as described in the first aspect.

[0064] Fourthly, embodiments of this application also provide a storage medium storing a computer program thereon, wherein when the computer program is executed by a processor, it implements the steps of the hardware status abnormality alarm monitoring method of the leaf root load measurement system as described in the first aspect.

[0065] As can be seen from the above technical solutions, this application has the following advantages:

[0066] The hardware status anomaly alarm monitoring method, device, equipment, and medium of the blade root load measurement system provided in this application achieve real-time monitoring and intelligent alarm of the wind turbine blade root load measurement system by comprehensively monitoring the key parameters of the fiber optic sensor and fiber optic demodulator, combined with time series analysis, fault prediction, and hierarchical early warning mechanisms. This improves the reliability and safety of system operation, reduces maintenance costs and equipment downtime, and provides strong support for the stable operation of wind turbines. Attached Figure Description

[0067] To more clearly illustrate the technical solution of this application, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0068] Figure 1 This is a flowchart illustrating the hardware status anomaly alarm monitoring method of the leaf root load measurement system of the present invention.

[0069] Figure 2 This is a schematic diagram of the hardware status abnormality alarm monitoring device of the leaf root load measurement system of the present invention. Detailed Implementation

[0070] The various embodiments of this disclosure will be described more fully in the following detailed description of the specific steps of the hardware status anomaly alarm monitoring method for the leaf root load measurement system. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0071] For example, wind turbine generators are the core devices in wind power generation that convert wind energy into electrical energy. Their operational safety and reliability have a direct and crucial impact on power generation efficiency and economic benefits. As one of the most important components of a wind turbine generator, the performance and condition of the blades play a vital role in the operation of the entire system. Therefore, accurately monitoring the load and vibration status of the blades has become a core element in ensuring the safe and stable operation of wind turbine generators.

[0072] Traditional methods for monitoring blade loads primarily utilize resistance strain gauges and mechanical sensors. However, these sensors are prone to performance degradation, signal weakening, or even malfunction when exposed to harsh environmental conditions such as high temperatures, humidity, and vibration, thus affecting measurement accuracy and system reliability. Furthermore, traditional sensors are susceptible to electromagnetic interference, leading to instability in data acquisition, which poses a potential hazard to the safe operation of wind turbine generators.

[0073] Fiber optic sensors, as an emerging monitoring method, work in conjunction with fiber Bragg grating demodulators to acquire sensor data. Due to their numerous advantages, including resistance to electromagnetic interference, high sensitivity, and good corrosion resistance, they are increasingly being applied in the field of wind power generation. Fiber optic sensors bear the crucial responsibility of collecting real-time physical data such as blade loads and vibrations, converting this data into corresponding optical signals, and then stably transmitting these signals to the fiber Bragg grating demodulator using the advantages of fiber optic transmission. The fiber Bragg grating demodulator establishes a correlation between the wavelength changes of the received optical signal and changes in external physical quantities such as strain and temperature, demodulating the optical signal to accurately reconstruct the data collected by the fiber optic sensor, thus achieving precise measurement of blade loads and vibrations. However, a significant problem with current fiber optic sensor systems is insufficient monitoring of hardware status. In practical applications, key parameters of the fiber Bragg grating demodulator and fiber optic sensors, such as wavelength, temperature, and power supply voltage, are not effectively monitored in real time. This leads to difficulties in responding quickly to faults, potentially causing equipment downtime or even safety accidents. Furthermore, it is currently impossible to distinguish between abnormal original wavelengths of the sensor (which may be due to abnormal blade strain or damage to the sensor itself) and abnormal output of the demodulator (demodulation errors caused by hardware failure), which can easily lead to misjudgments.

[0074] To address the aforementioned issues, this embodiment provides a hardware status anomaly alarm monitoring method for a blade root load measurement system, which comprehensively monitors the status of sensors and demodulators, provides early warnings of faults, and improves the reliability and safety of wind power systems.

[0075] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0076] Please see Figure 1The diagram shows a flowchart of a hardware status anomaly alarm monitoring method for a leaf root load measurement system in a specific embodiment. The method includes the following steps:

[0077] S1. Real-time acquisition of the raw wavelength signal output from the fiber optic sensor of the leaf root load measurement system. and the original wavelength signal The signal is transmitted to a fiber Bragg grating demodulator for demodulation, generating a demodulated wavelength signal. and load data electrical signals;

[0078] It should be noted that this step provides basic data support for subsequent monitoring and analysis, ensuring the real-time nature and accuracy of the data, which is a prerequisite for the effective operation of the entire monitoring system.

[0079] S2. Parameters of the fiber optic grating demodulator for the synchronous acquisition of leaf root load measurement system: operating temperature and power supply voltage ;

[0080] It should be noted that this step enables comprehensive monitoring of the demodulator's operating status, facilitating the timely detection of any abnormalities and ensuring the stable operation of the system.

[0081] S3. For the original wavelength signal Execution timing analysis:

[0082] Calculate the original wavelength signal within the set time window. mean and mean square deviation ;

[0083] Predict wavelength signal sequences over the next k periods using an autoregressive model;

[0084] The failure probability is determined using a support vector machine classification algorithm based on the predicted wavelength signal sequence. predict;

[0085] It should be noted that the time series analysis, which calculates the mean and standard deviation, predicts future wavelength signal sequences through an autoregressive model, and uses a support vector machine classification algorithm to predict the probability of failure, introduces data analysis and machine learning. This enables the system to predict potential failure risks in advance, giving it the ability to provide proactive early warnings and enhancing the system's intelligence level and the accuracy of fault diagnosis.

[0086] S4. Set the parameter threshold range for the fiber Bragg grating demodulator and calculate the demodulated wavelength signal. With preset standard wavelength Deviation;

[0087] It should be noted that this step provides a quantitative basis for determining whether the system is in a normal working state, making the alarm mechanism trigger reasonable and enabling timely and accurate identification of abnormal situations at the edge.

[0088] S5. Based on the original wavelength signal The time-series analysis results show the original wavelength signal. With demodulated wavelength signal The relationship between the parameters of the fiber Bragg grating demodulator and the threshold range of the parameters is used to implement graded early warning;

[0089] It should be noted that this step enables refined management and classification of system anomalies, allowing for timely responses to different anomalies, thus improving system security and reliability, and reducing equipment downtime and maintenance costs.

[0090] This embodiment accurately predicts faults by real-time acquisition and analysis of multi-dimensional data from fiber optic sensors and demodulators, enabling graded early warning and intelligent diagnosis, improving the operational stability of wind turbine generators, reducing equipment downtime risks, optimizing maintenance processes, and reducing maintenance costs.

[0091] Furthermore, as a refinement and extension of the specific implementation of the above embodiments, in order to fully illustrate the specific implementation process in this embodiment, another hardware status anomaly alarm monitoring method for a leaf root load measurement system is provided. This method includes the following steps:

[0092] S1. Real-time acquisition of the raw wavelength signal output from the fiber optic sensor of the leaf root load measurement system. and the original wavelength signal The signal is transmitted to a fiber Bragg grating demodulator for demodulation, generating a demodulated wavelength signal. and load data electrical signals;

[0093] S2. Parameters of the fiber optic grating demodulator for the synchronous acquisition of leaf root load measurement system: operating temperature and power supply voltage ;

[0094] The specific steps of step S2 are as follows:

[0095] S21. Obtain the operating temperature of the fiber Bragg grating demodulator using the built-in temperature sensor. ;

[0096] S22. The power supply voltage is acquired by connecting a voltage sensor in parallel at the power input terminal of the fiber Bragg grating demodulator, and the acquired analog voltage is converted into a digital signal by an analog-to-digital converter. The digital value of the power supply voltage is then read according to a preset sampling frequency.

[0097] S3. For the original wavelength signal Execution timing analysis:

[0098] Calculate the original wavelength signal within the set time window. mean and mean square deviation ;

[0099] Predict wavelength signal sequences over the next k periods using an autoregressive model;

[0100] The failure probability is determined using a support vector machine classification algorithm based on the predicted wavelength signal sequence. predict;

[0101] The specific steps of step S3 are as follows:

[0102] S31. Calculate the original wavelength signal within the set time window. mean :

[0103]

[0104] Where n is the number of sampling points of the original wavelength signal within the time window. It is the original wavelength signal of the i-th sampling point within the time window;

[0105] S32. Calculate the original wavelength signal within the set time window. mean square deviation :

[0106] ;

[0107] S33. Predict the wavelength sequence for the next k periods using the following autoregressive model:

[0108]

[0109] in, It is the order of the autoregressive model. It is the original wavelength signal at time t. It is a constant term. It is the autoregressive coefficient. It is a white noise error term. It is the original wavelength signal at time tj, that is, the wavelength value at the j-th time point before time t;

[0110] S34. Pre-build a training dataset and train the SVM classification model;

[0111] The specific steps of step S34 are as follows:

[0112] S341. Construct the training dataset:

[0113] Acquire historical normal wavelength signal sequences ;

[0114] in, The original wavelength signal of the i-th normal sampling point. It's a fault label. Indicates a normal state;

[0115] Collect historical fault wavelength sequences ;

[0116] in, The original wavelength signal of the i-th fault sampling point. This is a fault label; -1 indicates a fault status.

[0117] Specifically, Include:

[0118] Sensor detachment label

[0119] Label of broken optical fiber

[0120] Blade cracks ;

[0121] S342. Extract feature vectors for the training dataset:

[0122] ;

[0123] in, The mean within the window. The standard deviation within the window. It's a wavelength deviation. It is the white noise error term of the autoregressive residual;

[0124] S343. Constructing the decision function

[0125] in, Weight parameter vector, It is a constant term. Extracted feature vectors, It is a Gaussian kernel function. , It is the correlation coefficient, for example ;

[0126] Constructing a convex optimization problem function for the decision function:

[0127]

[0128]

[0129] in, It is a penalty factor (e.g., a value of 1.0), which controls the tolerance for misclassification; These are slack variables, allowing for some outliers to be misclassified; It is the magnitude of the normal vector of the classification hyperplane;

[0130] The optimal weight parameters are obtained by iteratively solving using the SMO algorithm. Optimal constant term ;

[0131] S35. Transform the predicted wavelength signal sequence for the next k periods into a feature vector. and the feature vector Input the trained SVM classification model to obtain the decision result; the feature vector This includes statistical features extracted from wavelength signal sequences;

[0132] The specific steps of step S35 are as follows:

[0133] S351. Calculate the real-time feature vector for the real-time window data:

[0134]

[0135] in, This is the average value within the real-time window. The standard deviation within the real-time window. It's a wavelength deviation. It is the white noise error term of the autoregressive residual;

[0136] S352. Based on optimal weight parameters Optimal constant term The decision function of the trained SVM model is obtained as follows:

[0137]

[0138] in, It is the distance from the data point to the hyperplane sign, representing the severity of the fault.

[0139] S353. Transfer the real-time feature vector Input the decision function of the trained SVM model and perform decision function calculation;

[0140] S36. The failure probability will be calculated based on the decision results. ;

[0141] In step S36, the failure probability is mapped based on the decision function calculation results:

[0142] ;

[0143] In step S3, the timing analysis uses a sliding window update:

[0144] Each new original wavelength signal Data points: Remove the oldest data point within the window and recalculate the original wavelength signal. mean and mean square deviation :

[0145]

[0146]

[0147] in, These are newly added raw wavelength signal data points. It is the oldest original wavelength signal data point within the time window. It is the number of sampling points of the original wavelength signal within the time window. This is the mean before the update. This is the updated mean. It is the mean squared error before the update. This is the updated mean squared error;

[0148] S4. Set the parameter threshold range for the fiber Bragg grating demodulator and calculate the demodulated wavelength signal. With preset standard wavelength Deviation;

[0149] The specific steps of step S4 are as follows:

[0150] S41. Set the normal operating range of the fiber Bragg grating demodulator parameters:

[0151] Operating temperature Normal working range ;

[0152] Power supply voltage Normal working range ;

[0153] Output wavelength Normal working range ;

[0154] S42. According to the inward contraction margin Set the correction range for the parameters of the fiber Bragg grating demodulator:

[0155] Operating temperature Scope of revision work ;

[0156] Power supply voltage Scope of revision work ;

[0157] Output wavelength Correction range ;

[0158] In step S42, the inward contraction margin Adaptive adjustment based on the historical operating conditions of the fiber Bragg grating demodulator:

[0159]

[0160] in, The historical standard deviation of the parameter, For safety factor;

[0161] S43. Calculate the demodulated wavelength signal With preset standard wavelength deviation ;

[0162] ;

[0163] S5. Based on the original wavelength signal The time-series analysis results show the original wavelength signal. With demodulated wavelength signal The relationship between the parameters of the fiber Bragg grating demodulator and the threshold range of the parameters is used to implement graded early warning;

[0164] The triggering conditions for the graded early warning in step S5 are as follows:

[0165] If the demodulated wavelength signal Compared with the original wavelength signal If the difference exceeds the set deviation and the duration exceeds the set time period, a hardware fault alarm for the fiber Bragg grating demodulator will be triggered.

[0166] If the predicted fault probability of the wavelength signal sequence Greater than the preset probability threshold Or set the original wavelength signal within the time window. mean square deviation Greater than the preset mean squared error threshold This triggers an abnormal alarm from the fiber optic sensor.

[0167] If the operating temperature of the fiber Bragg grating demodulator Power supply voltage and output wavelength If at least one of the following is outside the normal operating range, a severe alarm will be triggered on the fiber Bragg grating demodulator and the machine will be shut down.

[0168] If the operating temperature of the fiber Bragg grating demodulator Power supply voltage and output wavelength All are within the normal operating range, but if at least one exceeds the correction range, a minor alarm will be triggered on the fiber Bragg grating demodulator.

[0169] If the demodulated wavelength signal With preset standard wavelength deviation Greater than the preset deviation threshold If this occurs, it will trigger an accuracy alarm in the fiber Bragg grating demodulator.

[0170] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0171] like Figure 2 As shown, the following is an embodiment of the hardware status anomaly alarm monitoring device for the blade root load measurement system provided in this disclosure. This device and the hardware status anomaly alarm monitoring method for the blade root load measurement system in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the hardware status anomaly alarm monitoring device for the blade root load measurement system, please refer to the embodiments of the above-described hardware status anomaly alarm monitoring method for the blade root load measurement system.

[0172] The device includes:

[0173] The demodulation and signal acquisition module is used to acquire the raw wavelength signal output by the fiber optic sensor of the leaf root load measurement system in real time. and the original wavelength signal The signal is transmitted to a fiber Bragg grating demodulator for demodulation, generating a demodulated wavelength signal. and load data electrical signals;

[0174] The demodulator parameter acquisition module is used to synchronously acquire parameters of the fiber optic grating demodulator in the leaf root load measurement system, including operating temperature. and power supply voltage ;

[0175] The timing analysis module is used to analyze the original wavelength signal. Execution timing analysis:

[0176] Calculate the original wavelength signal within the set time window. mean and mean square deviation ;

[0177] Predict wavelength signal sequences over the next k periods using an autoregressive model;

[0178] The failure probability is determined using a support vector machine classification algorithm based on the predicted wavelength signal sequence. predict;

[0179] The parameter threshold setting module is used to set the parameter threshold range of the fiber Bragg grating demodulator and calculate the demodulated wavelength signal. With preset standard wavelength Deviation;

[0180] The status warning module is used to monitor the original wavelength signal. The time-series analysis results show the original wavelength signal. With demodulated wavelength signal The relationship between the parameters of the fiber Bragg grating demodulator and the threshold range of the parameters is used to implement graded early warning.

[0181] This embodiment achieves accurate fault prediction, hierarchical early warning and intelligent diagnosis by interactively coordinating the signal acquisition module before and after demodulation, the demodulator parameter acquisition module, the timing analysis module, the parameter threshold setting module, and the status early warning module, through real-time acquisition and analysis of multi-dimensional data from fiber optic sensors and demodulators. This effectively improves the operational stability of wind turbine generators, reduces equipment downtime risks, optimizes maintenance processes, and reduces maintenance costs.

[0182] The hardware status anomaly alarm monitoring method for the leaf root load measurement system provided in this application embodiment can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the electronic device includes, but is not limited to, laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0183] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0184] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device. In other embodiments of this application, the electronic device may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0185] A processor may include one or more processing units, such as a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0186] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0187] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0188] The aforementioned electronic equipment enables the real-time acquisition of the raw wavelength signal output by the fiber optic sensor of the blade root load measurement system, which is part of the hardware status anomaly alarm monitoring method of the blade root load measurement system of this application. and the original wavelength signal The signal is transmitted to a fiber Bragg grating demodulator for demodulation, generating a demodulated wavelength signal. and load data electrical signals; synchronously acquire parameters of the fiber optic grating demodulator of the leaf root load measurement system: operating temperature. and power supply voltage For the original wavelength signal Execution timing analysis: Calculate the original wavelength signal within a set time window. mean and mean square deviation Predict the wavelength signal sequence over the next k periods using an autoregressive model; then use a support vector machine classification algorithm to determine the fault probability based on the predicted wavelength signal sequence. Prediction; setting the parameter threshold range of the fiber Bragg grating demodulator and calculating the demodulated wavelength signal. With preset standard wavelength The deviation; based on the original wavelength signal The time-series analysis results show the original wavelength signal. With demodulated wavelength signal The technical solution for implementing graded early warning is based on the relationship between the parameters of the fiber optic demodulator and the threshold range of the parameters. This achieves accurate fault prediction by real-time acquisition and analysis of multi-dimensional data from fiber optic sensors and demodulators, enabling graded early warning and intelligent diagnosis, effectively improving the operational stability of wind turbine generators, reducing equipment downtime risks, optimizing maintenance processes, and reducing maintenance costs.

[0189] The storage medium provided in this application stores a program product capable of implementing a hardware status anomaly alarm monitoring method for a leaf root load measurement system.

[0190] The hardware status anomaly alarm monitoring method of the blade root load measurement system includes: real-time acquisition of the raw wavelength signal output by the fiber optic sensor of the blade root load measurement system. and the original wavelength signal The signal is transmitted to a fiber Bragg grating demodulator for demodulation, generating a demodulated wavelength signal. and load data electrical signals; synchronously acquire parameters of the fiber optic grating demodulator of the leaf root load measurement system: operating temperature. and power supply voltage For the original wavelength signal Execution timing analysis: Calculate the original wavelength signal within a set time window. mean and mean square deviation Predict the wavelength signal sequence over the next k periods using an autoregressive model; then use a support vector machine classification algorithm to determine the fault probability based on the predicted wavelength signal sequence. Prediction; setting the parameter threshold range of the fiber Bragg grating demodulator and calculating the demodulated wavelength signal. With preset standard wavelength The deviation; based on the original wavelength signal The time-series analysis results show the original wavelength signal. With demodulated wavelength signal The relationship between the parameters of the fiber Bragg grating demodulator and the threshold range of the parameters is used to implement graded early warning.

[0191] In some possible implementations, the hardware status anomaly alarm monitoring method of the leaf root load measurement system of this disclosure can be implemented as a program product, which includes program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0192] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0193] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for monitoring and alarming abnormal hardware status of a blade root load measurement system, characterized in that, Includes the following steps: S1. Real-time acquisition of the raw wavelength signal output from the fiber optic sensor of the leaf root load measurement system. and the original wavelength signal The signal is transmitted to a fiber Bragg grating demodulator for demodulation, generating a demodulated wavelength signal. and load data electrical signals; S2. Parameters of the fiber optic grating demodulator for the synchronous acquisition of leaf root load measurement system: operating temperature and power supply voltage ; S3. For the original wavelength signal Execution timing analysis: Calculate the original wavelength signal within the set time window. mean and mean square deviation ; Predict wavelength signal sequences over the next k periods using an autoregressive model; The failure probability is determined using a support vector machine classification algorithm based on the predicted wavelength signal sequence. predict; S4. Set the parameter threshold range for the fiber Bragg grating demodulator and calculate the demodulated wavelength signal. With preset standard wavelength The deviation; the specific steps of step S4 are as follows: S41. Set the normal operating range of the fiber Bragg grating demodulator parameters: Operating temperature Normal working range ; Power supply voltage Normal working range ; Output wavelength Normal working range ; S42. According to the inward contraction margin Set the correction range for the parameters of the fiber Bragg grating demodulator: Operating temperature Scope of revision work ; Power supply voltage Scope of revision work ; Output wavelength Correction range ; S43. Calculate the demodulated wavelength signal With preset standard wavelength deviation ; ； S5. Based on the original wavelength signal The time-series analysis results show the original wavelength signal. With demodulated wavelength signal The relationship between the parameters of the fiber Bragg grating demodulator and the threshold range of the parameters is used to execute a graded early warning; the triggering conditions for the graded early warning in step S5 are as follows: If the demodulated wavelength signal Compared with the original wavelength signal If the difference exceeds the set deviation and the duration exceeds the set time period, a hardware fault alarm for the fiber Bragg grating demodulator will be triggered. If the predicted fault probability of the wavelength signal sequence Greater than the preset probability threshold Or set the original wavelength signal within the time window. mean square deviation Greater than the preset mean squared error threshold This triggers an abnormal alarm from the fiber optic sensor. If the operating temperature of the fiber Bragg grating demodulator Power supply voltage and output wavelength If at least one of the following is outside the normal operating range, a severe alarm will be triggered on the fiber Bragg grating demodulator and the machine will be shut down. If the operating temperature of the fiber Bragg grating demodulator Power supply voltage and output wavelength All are within the normal operating range, but if at least one exceeds the correction range, a minor alarm will be triggered on the fiber Bragg grating demodulator. If the demodulated wavelength signal With preset standard wavelength deviation Greater than the preset deviation threshold If this occurs, it will trigger an accuracy alarm in the fiber Bragg grating demodulator.

2. The hardware status abnormality alarm monitoring method for the leaf root load measurement system according to claim 1, characterized in that, The specific steps of step S2 are as follows: S21. Obtain the operating temperature of the fiber Bragg grating demodulator using the built-in temperature sensor. ; S22. The power supply voltage is acquired by connecting a voltage sensor in parallel at the power input terminal of the fiber Bragg grating demodulator, and the acquired analog voltage is converted into a digital signal by an analog-to-digital converter. The digital value of the power supply voltage is then read according to a preset sampling frequency.

3. The hardware status abnormality alarm monitoring method for the blade root load measurement system according to claim 1, characterized in that, The specific steps of step S3 are as follows: S31. Calculate the original wavelength signal within the set time window. mean : Where n is the number of sampling points of the original wavelength signal within the time window. It is the original wavelength signal of the i-th sampling point within the time window; S32. Calculate the original wavelength signal within the set time window. mean square deviation : ； S33. Predict the wavelength sequence for the next k periods using the following autoregressive model: in, It is the order of the autoregressive model. It is the original wavelength signal at time t. It is a constant term. It is the autoregressive coefficient. It is a white noise error term. It is the original wavelength signal at time tj, that is, the wavelength value at the j-th time point before time t; S34. Pre-build a training dataset and train the SVM classification model; S35. Transform the predicted wavelength signal sequence for the next k periods into a feature vector. and the feature vector Input the trained SVM classification model to obtain the decision result; the feature vector This includes statistical features extracted from wavelength signal sequences; S36. The failure probability will be calculated based on the decision results. .

4. The hardware status abnormality alarm monitoring method for the leaf root load measurement system according to claim 1 or 3, characterized in that, In step S3, the timing analysis uses a sliding window update: Each new original wavelength signal Data points: Remove the oldest data point within the window and recalculate the original wavelength signal. mean and mean square deviation : in, These are newly added raw wavelength signal data points. It is the oldest original wavelength signal data point within the time window. It is the number of sampling points of the original wavelength signal within the time window. This is the mean before the update. This is the updated mean. It is the mean squared error before the update. This is the updated mean squared error.

5. The hardware status abnormality alarm monitoring method for the leaf root load measurement system according to claim 1, characterized in that, In step S42, the inward contraction margin Adaptive adjustment based on the historical operating conditions of the fiber Bragg grating demodulator: in, The historical standard deviation of the parameter, This is for the safety factor.

6. A hardware status anomaly alarm monitoring device for a leaf root load measurement system, employing the method described in any one of claims 1-5, characterized in that, include: The demodulation and signal acquisition module is used to acquire the raw wavelength signal output by the fiber optic sensor of the leaf root load measurement system in real time. and the original wavelength signal The signal is transmitted to a fiber Bragg grating demodulator for demodulation, generating a demodulated wavelength signal. and load data electrical signals; The demodulator parameter acquisition module is used to synchronously acquire parameters of the fiber optic grating demodulator in the leaf root load measurement system, including operating temperature. and power supply voltage ; The timing analysis module is used to analyze the original wavelength signal. Execution timing analysis: Calculate the original wavelength signal within the set time window. mean and mean square deviation ; Predict wavelength signal sequences over the next k periods using an autoregressive model; The failure probability is determined using a support vector machine classification algorithm based on the predicted wavelength signal sequence. predict; The parameter threshold setting module is used to set the parameter threshold range of the fiber Bragg grating demodulator and calculate the demodulated wavelength signal. With preset standard wavelength Deviation; The status warning module is used to monitor the original wavelength signal. The time-series analysis results show the original wavelength signal. With demodulated wavelength signal The relationship between the parameters of the fiber Bragg grating demodulator and the threshold range of the parameters is used to implement graded early warning.

7. An electronic 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 program, it implements the steps of the hardware status abnormality alarm monitoring method of the leaf root load measurement system as described in any one of claims 1 to 5.

8. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the hardware status abnormality alarm monitoring method of the leaf root load measurement system as described in any one of claims 1 to 5.

Images