Blade structure damage fault diagnosis method, system and electronic equipment

Abstract

This invention relates to a method, system, and electronic device for diagnosing blade structural damage. The method includes acquiring vibration data; determining a deviation index based on the vibration data according to a sudden risk assessment rule; determining a sudden risk parameter based on the deviation index and a risk conversion rule; outputting an alarm message if the sudden risk parameter equals an alarm preset value; determining a damage risk parameter based on the damage assessment rule and the vibration data if the sudden risk parameter does not equal the alarm preset value; and outputting a prompt message based on the damage risk parameter and a risk level rule. This invention improves the accuracy of blade structural damage diagnosis results.

Description

Technical Field

[0001] This application relates to the technical field of fault diagnosis, and in particular to a method, system and electronic device for diagnosing blade structural damage faults. Background Technology

[0002] With the rapid development of the new energy industry, wind power is particularly prominent. The reliable operation of wind turbine generators directly affects energy conversion efficiency, thus the safe operation of wind turbine generators has received increasing attention. Blades are a crucial component of wind turbine generators; they receive wind energy, drive the transmission chain, and ultimately output electrical energy. However, blades operate in harsh environments such as wind, frost, rain, snow, and ice for extended periods, and are subjected to various alternating loads such as wind loads, gravity, and centrifugal force. This makes them highly susceptible to structural damage such as cracks, fissures, and buckling. If not detected in time, these damages can even lead to breakage, directly impacting the safety and reliability of the wind turbine operation.

[0003] Blade structural damage often involves early cracking, slow propagation, and structural stiffness degradation. Therefore, in the later stages of structural damage development, the structural load-bearing capacity may be unable to cope with sudden extreme wind conditions. At the same time, blades are also prone to sudden and severe structural damage when encountering external emergencies such as lightning strikes, icing, and tower sweeping.

[0004] Currently, most fault diagnosis methods for blade structural damage focus on modal testing and data-driven anomaly detection methods. Modal testing-based diagnostic methods are mostly based on natural frequency shifts to identify blade crack damage. The advantage of this type of method is that it does not require a large number of training samples. The disadvantage is that modal parameters in actual engineering are difficult to obtain and deviate from design values. This deviation is difficult to quantify or calculate in advance, often introducing uncertainty into the diagnostic analysis and leading to false alarms and missed alarms. Anomaly detection methods have the advantage of not relying on fault samples; models trained only on samples under normal conditions can determine the current state of the blade. However, to adapt to different operating conditions, this type of method requires a large amount of data under normal conditions as training samples, or requires training multiple models for different operating conditions for blade damage assessment. This type of algorithm is sensitive to factors such as turbine location, turbine type, and blade model, requiring retraining and learning for each wind turbine.

[0005] The existing technical solutions mentioned above have the following drawbacks: the accuracy of the diagnostic results is low, and it is easy to miss or misreport. Summary of the Invention

[0006] To improve the accuracy of blade structural damage fault diagnosis results, this application provides a blade structural damage fault diagnosis scheme.

[0007] In a first aspect of this application, a method for diagnosing blade structural damage is provided. The method includes: acquiring vibration data;

[0008] Based on the vibration data and in accordance with the rules for assessing sudden risks, the deviation index is determined.

[0009] Determine the parameters for sudden risks based on the deviation index and risk conversion rules;

[0010] If the sudden risk parameter is equal to the alarm preset value, then an alarm message is output;

[0011] If the sudden risk parameter is not equal to the alarm preset value, then the damage risk parameter is determined according to the damage assessment rules and the vibration data;

[0012] Based on the damage risk parameters and risk level rules, output a prompt message.

[0013] By employing the above technical solution, the acquired vibration data is calculated in two parts. First, based on the vibration data and the sudden risk assessment rules, a deviation index is calculated. Then, based on the deviation index and risk conversion rules, a sudden risk parameter is determined. By judging whether the sudden risk parameter equals the alarm preset value, it is determined whether there is sudden structural damage to the blade. If so, an alarm message is directly output. Conversely, if the sudden risk parameter does not equal the alarm preset value, it indicates that there is no sudden structural damage to the blade. In this case, the damage risk parameter is calculated based on the vibration data and damage assessment rules. The degree of blade damage is determined by the damage risk parameter and risk level rules, and a prompt message is output based on the degree of damage. By calculating the sudden risk parameter and damage risk parameter based on the vibration data and using different calculation rules to judge both sudden and non-sudden damage to the blade, the accuracy of blade structural damage diagnosis results is improved.

[0014] In a preferred embodiment, this application can be further configured such that acquiring vibration data includes:

[0015] Obtain monitoring data;

[0016] According to the preset screening rules, the monitoring data is screened for quality to obtain the first target data;

[0017] The first target data is filtered to obtain vibration data.

[0018] In a preferred embodiment, this application can be further configured such that: determining the deviation index based on the vibration data according to the sudden risk assessment rules includes:

[0019] The deviation index includes oscillation deviation and peak deviation, and the vibration data includes oscillation data and waving data;

[0020] Based on the oscillation data, determine the peak oscillation index;

[0021] Based on the waving data, determine the peak waving index;

[0022] Determine the oscillation deviation based on the peak oscillation index;

[0023] Determine the degree of wave deviation based on the wave peak index.

[0024] In a preferred embodiment, this application can be further configured as follows: determining the sudden risk parameters based on the deviation index and risk conversion rules includes:

[0025] When both the deviation index, namely the swing deviation and the waving deviation, are lower than the preset deviation value, the sudden risk parameter is determined to be 1;

[0026] When either the swing deviation or the waving deviation is higher than the preset deviation value, or both are higher than the preset deviation value, the sudden risk parameter is 0.

[0027] In a preferred embodiment, this application can be further configured as follows: if the sudden risk parameter is not equal to the alarm preset value, then the damage risk parameter is determined according to the damage assessment rules and the vibration data, including:

[0028] When the sudden risk parameter is not within the alarm threshold range, the vibration data is subjected to wavelet noise reduction processing to determine the second target data;

[0029] Obtain historical complexity metrics;

[0030] Based on the second target data and complexity rules, determine the complexity index;

[0031] Based on the aforementioned complexity index and historical complexity index, determine the longitudinal damage parameters;

[0032] The lateral damage parameters are determined based on multiple sets of complexity indicators;

[0033] Damage risk parameters are determined based on the transverse damage parameters and the longitudinal damage parameters.

[0034] In a preferred embodiment, this application can be further configured to: determine damage risk parameters based on the transverse damage parameters and the longitudinal damage parameters, including:

[0035] If both the transverse damage parameter and the longitudinal damage parameter are within the alarm threshold range, then the larger of the transverse damage parameter and the longitudinal damage parameter is the damage risk parameter.

[0036] If either the lateral damage parameter or the longitudinal damage parameter is outside the alarm threshold range, or if neither of them is outside the alarm threshold range, then the smaller of the lateral damage parameter and the longitudinal damage parameter is the damage risk parameter.

[0037] In a preferred embodiment, this application can be further configured to: output prompt information based on the damage risk parameters and risk level rules, including:

[0038] Based on the risk level rules, obtain the correspondence between the damage risk parameters and the damage level;

[0039] The damage level is determined based on the aforementioned correspondence;

[0040] Based on the damage level, output a prompt message.

[0041] In a second aspect of this application, a blade structure damage fault diagnosis system is provided. The system includes:

[0042] The data acquisition module is used to acquire vibration data;

[0043] The data processing module is used to determine the second target data based on the vibration data;

[0044] The sudden risk calculation module is used to determine the deviation index based on the vibration data;

[0045] The emergency risk assessment module is used to determine emergency risk parameters and output alarm information based on the deviation index and risk conversion rules.

[0046] The damage risk calculation module is used to determine damage risk parameters based on the second target data and damage assessment rules;

[0047] The damage risk determination module is used to output prompt information based on the damage risk parameters.

[0048] In a third aspect of this application, an electronic device is provided. The electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the blade structure damage fault diagnosis method as described above.

[0049] In a fourth aspect of this application, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the method according to the first aspect of this application.

[0050] In summary, this application includes at least one of the following beneficial technical effects:

[0051] 1. Based on vibration data and sudden risk assessment rules, a deviation index is calculated. Then, based on the deviation index and risk conversion rules, sudden risk parameters are determined. By checking whether the sudden risk parameters equal the alarm preset value, it is determined whether there is sudden structural damage to the blade. If so, an alarm message is directly output. Conversely, if the sudden risk parameters do not equal the alarm preset value, it indicates that there is no sudden structural damage to the blade. In this case, damage risk parameters are calculated based on vibration data and damage assessment rules. The degree of blade damage is determined using damage risk parameters and risk level rules, and a prompt message is output based on the degree of damage. By combining vibration data with different calculation rules to derive sudden risk parameters and damage risk parameters, and by judging from both sudden and non-sudden damage to the blade, the accuracy of blade structural damage diagnosis results is improved.

[0052] 2. Using the second target data and complexity rules, the complexity index is calculated. Then, based on the complexity index, the longitudinal damage parameter and the transverse damage parameter are determined respectively. In the calculation of the damage risk parameter, the degree of blade damage is considered from two aspects by calculating the longitudinal damage parameter and the transverse damage parameter, which further improves the accuracy of the damage risk parameter and reduces the problem of false alarms or missed alarms. Attached Figure Description

[0053] Figure 1 This is a flowchart illustrating the blade structure damage fault diagnosis method provided in this application.

[0054] Figure 2 This is a schematic diagram of the blade structure damage fault diagnosis system provided in this application.

[0055] Figure 3 This is a schematic diagram of the structure of the electronic device provided in this application.

[0056] In the diagram, 200 is the blade structure damage fault diagnosis system; 201 is the data acquisition module; 202 is the data processing module; 203 is the sudden risk calculation module; 204 is the sudden risk judgment module; 205 is the damage risk calculation module; 206 is the damage risk determination module; 301 is the CPU; 302 is the ROM; 303 is the RAM; 304 is the I / O interface; 305 is the input section; 306 is the output section; 307 is the storage section; 308 is the communication section; 309 is the driver; and 310 is the removable medium. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0058] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0059] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0060] This application provides a method for diagnosing blade structural damage faults. The main process of the method is described below.

[0061] like Figure 1 As shown:

[0062] Step S101: Acquire vibration data.

[0063] Specifically, before acquiring data, the sensors for data acquisition must first be installed. The determination of sensor installation locations is based on three methods: strength analysis reports from the blade design phase, static load test or fatigue load test reports of the full-size blades, or industry expert experience. Once the sensor installation locations are determined, the sensors, data acquisition equipment, and server need to be installed accordingly, and connecting cables need to be laid appropriately for data acquisition. During data acquisition, data quality abnormalities may occur due to sensor damage, loose sensor cable connections, or electromagnetic interference. Abnormal data quality can lead to inaccurate data reflecting the actual vibration status of the equipment and may cause false alarms. Therefore, the acquired data needs to be filtered according to preset filtering rules, and diagnostic analysis should be performed on the data that meets the requirements. These filtering rules include removing and cleaning data with quality problems such as data drift, data interruption, and data exceeding the range. Specifically, this includes data drift anomaly detection, which involves calculating the mean of data in segments; when the mean of any segment deviates significantly from the zero line, the vibration data is considered to have drifted; data interruption anomaly detection, which uses a sliding window algorithm to calculate the root mean square of the data in segments; when the root mean square value decreases significantly, the data is considered to have been interrupted; sensor range exceedance anomaly detection, which checks whether the data amplitude exceeds the sensor's range; when it does, the data is considered abnormal; positive and negative data point difference ratio anomaly detection, which checks whether the difference in the number of positive and negative data points is large; and vibration data multiple repetition anomaly detection, which checks whether there are many repeated points in the data; if the proportion of repeated points is large, the data is considered abnormal. Abnormal data is removed to obtain the first target data. In this embodiment, the first target data consists of six sets of data collected from the three blades in the flapping and oscillating directions, denoted as EV_1, FV_1, EV_2, FV_2, EV_3, and FV_3, respectively. These six sets of data are subjected to high-pass filtering to eliminate interference from blade rotation. The six sets of data after high-pass filtering are vibration data, denoted as edge1, flap1, edge2, flap2, edge3, and flap3, respectively. Specifically, flapping and oscillating refer to the following: facing the head of the machine, clockwise rotation of the impeller is considered positive; movement along the impeller's direction is flapping (perpendicular to the head); and movement parallel to the head is oscillating.

[0064] Step S102: Determine the deviation index based on vibration data according to the rules for assessing sudden risks.

[0065] Specifically, the vibration data includes oscillation data and flapping data. The oscillation data includes the oscillation data of the first blade (edge1), the second blade (edge2), and the third blade (edge3). The flapping data includes the flapping data of the first blade (flap1), the second blade (flap2), and the third blade (flap3). Based on the flapping data, the flapping peak index is calculated. Taking the flapping data of the first blade as an example, the calculation formula is: pp_flap1 = max(flap1) - min(flap1). Similarly, the oscillation peak index can be calculated based on the oscillation data. The results of the six sets of data are recorded as follows:

[0066] pp_edge1,pp_flap1,pp_edge2,pp_flap2,pp_edge3,pp_flap3.

[0067] Next, it is necessary to determine the swing deviation based on the swing peak index and the wave deviation based on the wave peak index. After the peak index of the above six sets of data is calculated, the deviation index is calculated based on the peak index of the six sets of data. The above deviation index includes the swing deviation and the wave deviation. Taking the swing direction as an example, the calculation formula is as follows: [pp_edge1,pp_edge2,pp_edge3] / max([pp_edge1,pp_edge2,pp_edge3]).

[0068] According to the above calculation formula, the swing deviation and the oscillation deviation can be obtained. The swing deviation consists of three swing data deviations, and the oscillation deviation consists of three oscillation data deviations.

[0069] Step S103: Determine the parameters for sudden risks based on the deviation index and risk conversion rules.

[0070] Specifically, when both the aforementioned oscillation deviation and the aforementioned waving deviation are lower than the preset deviation value, the sudden risk parameter is set to 1; when either the aforementioned oscillation deviation or the aforementioned waving deviation is higher than the preset deviation value, or both are higher than the preset deviation value, the sudden risk parameter is set to the default value for sudden parameters. In this embodiment, the default value for sudden parameters is 0, and the preset deviation value is 0.5. That is, it is determined whether both the waving deviation and the oscillation deviation have two data deviation indicators less than 0.5. If so, it indicates that the peak value has deviated. Specifically, if the peak value of the first blade is 8 m / s... 2 The second and third blades are both 3 m / s 2The calculated deviation index is [1, 0.375, 0.375]. Since the deviation indices of the second and third blades are both less than 0.5, it can be considered that there is sudden structural damage, and an alarm is directly triggered. That is, the sudden risk parameter of the first blade is recorded as 1. For blades where no sudden damage is detected, the sudden risk parameter is output using the default value, i.e., the sudden risk parameter is 0. If no sudden structural damage is detected at all, the next step of data processing is performed.

[0071] By comparing the results of the waving deviation in the waving direction and the sway deviation in the sway direction, the influence of interference signals in individual directions can be eliminated. For example, if there is an isolated impact component in the signal, the peak value in a single direction may be very large, which in turn affects the calculation of the deviation indices of the three directions and causes false alarms of sudden structural damage to the blade.

[0072] Step S104: If the sudden risk parameter is equal to the alarm preset value, then output the alarm information.

[0073] Specifically, in this embodiment, the alarm preset value is 1. When the sudden risk parameter is 1, it indicates that the blade has sudden structural damage, and an alarm signal is directly output to prompt the staff to take appropriate measures in a timely manner.

[0074] Step S105: If the sudden risk parameter is not equal to the alarm preset value, then determine the damage risk parameter according to the damage assessment rules and vibration data.

[0075] When the above-mentioned sudden risk parameters are not equal to the alarm preset value, the above vibration data will be subjected to wavelet denoising processing, that is, wavelet denoising processing will be performed on EV_1, FV_1, EV_2, FV_2, EV_3 and FV_3 respectively to determine the second target data. Wavelet denoising processing can eliminate noise interference and avoid noise signals affecting the calculation results of complexity indicators in subsequent calculations.

[0076] Based on the second objective data and complexity rules mentioned above, the complexity index is determined.

[0077] Specifically, the aforementioned second target data is decomposed into n frequency bands. In this embodiment, the six groups of signals are sequentially decomposed into n frequency bands, with a total number of frequency bands of 6*n. The maximum number of decompositions n is selected as shown in the following formula: Assuming the data length of a group of signals is N, N=2^L, then n=L / 2. Based on the energy distribution in each frequency band, the complexity index of the second target data is calculated. The calculation results are denoted as div_edge_1, div_flap_1, div_edge_2, div_flap_2, div_edge_3, and div_flap_3, respectively. Taking the oscillation direction as an example, the specific calculation formula is as follows:

[0078] div_edge_i=-∑eng_edge_i_j×log(2, eng_edge_i_j) (j＝1,2,...n) ;

[0079] Wherein, eng_edge_i_j is the proportion of the energy of the j-th frequency band in the oscillation direction of blade i in the total energy of all frequency bands, and eng_flap_i_j is the proportion of the energy of the j-th frequency band in the flapping direction of blade i in the total energy of all frequency bands. Similarly, the complexity index of the flapping direction can be calculated.

[0080] Obtain historical complexity metrics, and determine longitudinal damage parameters based on the aforementioned complexity metrics and historical complexity metrics.

[0081] Specifically, the complexity index of historical data for each channel under specified operating conditions is obtained, i.e., the historical complexity index. When the complexity index exceeds the proportion of historical complexity indices for that blade in that direction, the longitudinal damage parameters of each blade are calculated. The longitudinal damage parameters of each blade are denoted as his1_edge, his1_flap, his2_edge, his2_flap, his3_edge, and his3_flap, respectively. For example, assuming the complexity index of the first blade's oscillation direction is 0.75, the calculation results of the first blade's oscillation direction are compared with the historical data from 100 packets under specified operating conditions. Based on the proportion exceeding the historical results, [0, 0.2] is normal, [0.2, 0.4] is of concern, [0.4, 0.6] is a warning, and [0.6, 1] is an alarm. If the current complexity index exceeds the historical complexity index for 0 to 20 packets, the score is [0, 0.2]; if it exceeds for 20 to 40 packets, the score is [0.2, 0.4]; if it exceeds for 40 to 60 packets, the score is [0.4, 0.6]; and if it exceeds for 60 to 100 packets, the score is [0.6, 1]. For example, if the complexity index for the first blade's oscillation direction is 0.75, exceeding the historical complexity index for 70 packets, then his1_edge = 0.7. The above-mentioned operating conditions refer to the wind turbine operating at over 80% of its full power.

[0082] Based on multiple sets of complexity data, the lateral damage parameters are determined.

[0083] Specifically, the complexity indices of the oscillation and flapping directions of the first, second, and third blades are compared with the complexity indices of the oscillation and flapping directions of the three blades. Referring to the formula for calculating the deviation of peak indices from each other, the lateral damage parameters of each blade are calculated and denoted as com1_edge, com1_flap, com2_edge, com2_flap, com3_edge, and com3_flap, respectively. For example, the complexity index of the oscillation direction of the first blade is 0.75, the complexity index of the oscillation direction of the second blade is 0.25, and the complexity index of the oscillation direction of the third blade is 0.35. Referring to the calculation formula for the deviation of peak indicators, the deviation of the computational complexity indicator is [1, 0.33, 0.46], and the deviation threshold is set to [1, 0.75, 0.5, 0.25]. That is, when two or more deviation calculation results are between [1, 0.75], all three blades are normal, and the output lateral damage parameter is [0, 0, 0]. When the deviation is between [0.75, 0.5], the blade with a deviation of 1 is considered a focus, and the calculation result after combining the minimum deviation value with the threshold is taken as the output, while the other two blades are normal. When the deviation is between [0.5, 0.25], the blade with a deviation of 1 is a warning, and the calculation result after combining the minimum deviation value with the threshold is taken as the output, while the other two blades are normal. When the deviation is between [0.25, 0], the blade with a deviation of 1 is an alarm, and the calculation result after combining the minimum deviation value with the threshold is taken as the output, while the other two blades are normal. In this embodiment, the lateral damage parameters are calculated for the deviation range [1, 0.33, 0.46]. The factor values ​​are [1, 0.6, 0.4, 0.2, 0], and the deviation threshold is [1, 0.75, 0.5, 0.25, 0]. There is a mapping relationship between the above factor values ​​and the deviation threshold. The specific calculation is as follows: If 0.33 and 0.46 in [1, 0.33, 0.46] are within the range of [0.5, 0.25], then leaf 1 is in a warning state, and the other two leaves are normal. Based on the above mapping relationship, we can obtain 0.4 / 0.5 = x / (1-0.33), x = 0.536; 0.4 / 0.5 = x / (1-0.46), x = 0.432; In summary, since it is mentioned above that "the blade with a deviation of 1 between [0.5, 0.25] is a warning, and the calculation result after combining the minimum deviation value with the threshold is taken as the output", the calculation result corresponding to 0.33 is taken as the lateral damage parameter of the first blade, that is, com1_edge = 0.536.

[0084] Based on the aforementioned transverse damage parameters and longitudinal damage parameters, damage risk parameters are determined, including: if both the transverse damage parameters and longitudinal damage parameters are within the alarm threshold range, then the larger of the transverse damage parameters and longitudinal damage parameters is the damage risk parameter; if either the transverse damage parameters or longitudinal damage parameters are not within the alarm threshold range, then the smaller of the transverse damage parameters and longitudinal damage parameters is the damage risk parameter.

[0085] Specifically, when the aforementioned transverse and longitudinal damage parameters are within the normal range: the minimum of the two factor values ​​is taken as the final result for that blade in that direction; when both the transverse and longitudinal factor values ​​are abnormal: the maximum of the two factor values ​​is taken as the final result for that blade in that direction. For the first blade in the above calculation, the final factor value for the oscillation direction is 0.7. For a single blade, the maximum factor value in both directions is taken as the final result, and the final risk factor values ​​for each blade are output, denoted as factor1, factor2, and factor3.

[0086] Step S106: Output prompt information based on damage risk parameters and risk level rules.

[0087] Specifically, alarm thresholds are set for damage risk parameters, which are divided into four levels: 0 to 0.2 for normal, 0.2 to 0.4 for attention, 0.4 to 0.6 for warning, and 0.6 to 1 for alarm. Based on the value of the damage risk parameter, alarm information, warning information, attention information, or normal information is output.

[0088] This application provides a blade structure damage fault diagnosis system 200, referring to... Figure 2 The blade structure damage fault diagnosis system 200 includes:

[0089] Data acquisition module 201 is used to acquire vibration data;

[0090] Data processing module 202 is used to determine second target data based on the vibration data;

[0091] The sudden risk calculation module 203 is used to determine the deviation index based on the vibration data;

[0092] The sudden risk assessment module 204 is used to determine the sudden risk parameters and output alarm information based on the deviation index and risk conversion rules.

[0093] The damage risk calculation module 205 is used to determine damage risk parameters based on the second target data and damage assessment rules;

[0094] The damage risk determination module 206 is used to output prompt information based on the damage risk parameters.

[0095] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the described module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0096] This application discloses an electronic device. (Refer to...) Figure 3 The electronic device includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes based on a program stored in a read-only memory (ROM) 302 or a program loaded from a storage section 307 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus. An input / output (I / O) interface 304 is also connected to the bus.

[0097] The following components are connected to I / O interface 304: an input section 305 including a keyboard, mouse, etc.; an output section 306 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 307 including a hard disk, etc.; and a communication section 308 including a network interface card such as a LAN card, modem, etc. The communication section 308 performs communication processing via a network such as the Internet. A drive 309 is also connected to I / O interface 304 as needed. A removable medium 310, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 309 as needed so that computer programs read from it can be installed into storage section 307 as needed.

[0098] Specifically, according to embodiments of this application, the flowchart above refers to... Figure 1 The described process can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a machine-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 308, and / or installed from removable medium 310. When the computer program is executed by central processing unit (CPU) 301, it performs the functions defined in the apparatus of this application.

[0099] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can 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 of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer 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. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0100] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. A method for diagnosing blade structural damage, characterized in that, include: Acquire vibration data; determine the deviation index based on the vibration data according to the sudden risk assessment rules; determine the sudden risk parameters according to the deviation index and the risk conversion rules; If the sudden risk parameter is equal to the alarm preset value, then an alarm message is output; If the sudden risk parameter is not equal to the alarm preset value, then the damage risk parameter is determined according to the damage assessment rules and the vibration data; Based on the damage risk parameters and risk level rules, output a prompt message; The step of determining deviation indices based on the vibration data according to the sudden risk assessment rules includes: the deviation indices include sway deviation and peak deviation; the vibration data includes sway data and waving data; determining the sway peak index based on the sway data; determining the waving peak index based on the waving data; determining the sway deviation based on the sway peak index; determining the waving deviation based on the waving peak index; and determining the waving deviation based on the waving peak index. If the sudden risk parameter is not equal to the alarm preset value, then determining the damage risk parameter according to the damage assessment rules and the vibration data includes: when the sudden risk parameter is not within the alarm threshold range, performing wavelet noise reduction on the vibration data to determine the second target data; obtaining historical complexity indices; determining complexity indices based on the second target data and complexity rules; determining longitudinal damage parameters based on the complexity indices and historical complexity indices; determining transverse damage parameters based on multiple sets of complexity indices; and determining damage risk parameters based on the transverse damage parameters and the longitudinal damage parameters.

2. The blade structure damage fault diagnosis method according to claim 1, characterized in that, The process of acquiring vibration data includes: acquiring monitoring data; performing quality screening on the monitoring data according to preset screening rules to obtain first target data; and performing filtering processing on the first target data to obtain vibration data.

3. The blade structure damage fault diagnosis method according to claim 1, characterized in that, The step of determining the sudden risk parameter based on the deviation index and risk conversion rule includes: when the deviation index, namely the swing deviation and the waving deviation, are both lower than the deviation preset value, the sudden risk parameter is determined to be 1; when either the swing deviation or the waving deviation is higher than the deviation preset value or both are higher than the deviation preset value, the sudden risk parameter is 0.

4. The blade structure damage fault diagnosis method according to claim 1, characterized in that, Based on the lateral damage parameter and the longitudinal damage parameter, a damage risk parameter is determined, including: if both the lateral damage parameter and the longitudinal damage parameter are within the alarm threshold range, then the larger of the lateral damage parameter and the longitudinal damage parameter is the damage risk parameter; if either the lateral damage parameter or the longitudinal damage parameter is not within the alarm threshold range, or neither is within the alarm threshold range, then the smaller of the lateral damage parameter and the longitudinal damage parameter is the damage risk parameter.

5. The blade structure damage fault diagnosis method according to claim 1, characterized in that, The step of outputting prompt information based on the damage risk parameters and risk level rules includes: obtaining the correspondence between the damage risk parameters and damage levels according to the risk level rules; determining the damage level according to the correspondence; and outputting prompt information according to the damage level.

6. A blade structure damage fault diagnosis system, employing the blade structure damage fault diagnosis method as described in claim 1, characterized in that... include: The data acquisition module (201) is used to acquire vibration data; The data processing module (202) is used to determine the second target data based on the vibration data; The sudden risk calculation module (203) is used to determine the deviation index based on the vibration data; the sudden risk judgment module (204) is used to determine the sudden risk parameters and output alarm information based on the deviation index and risk conversion rules. The damage risk calculation module (205) is used to determine the damage risk parameters based on the second target data and the damage assessment rules; The damage risk determination module (206) is used to output prompt information based on the damage risk parameters.

7. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and executed as described in any one of claims 1 to 5.

Images