Method, device, equipment and medium for monitoring high-strength bolt faults of wind turbines

Abstract

The present application discloses a method, device, equipment and medium for monitoring the fault of high-strength bolts of wind turbines, and relates to the technical field of wind turbine status monitoring, including: determining the target high-strength bolts to be monitored in the target components of the wind turbine; detecting the impact and stress impact and bolt loosening angle change generated by the target high-strength bolts through the impact and angle composite sensor to obtain multiple feature information, and extracting features from the multiple feature information to obtain initial feature data; preprocessing the initial feature data to obtain target feature data; and making a comprehensive decision based on the target feature data whether the target high-strength bolt has a fault and the corresponding fault mode and fault location. The present application can extract features of the impact and angle change of the bolts through the impact and angle composite sensor installed on the bolts, and can achieve accurate identification and precise positioning of various bolt faults through comprehensive analysis of the feature extracted data.

Description

Technical Field

[0001] The present application relates to the technical field of wind turbine status monitoring, and in particular to a method, device, equipment and medium for monitoring faults of high-strength bolts of wind turbines. Background Art

[0002] Wind turbines are expensive, and are used in harsh environments and complex working conditions. The high-strength connecting bolts between various components are subjected to the combined effects of various loads such as vibration, torsion, and shear during operation. At present, with the increase in the number of wind turbines put into use and the increase in service life, the number of units with broken and loose high-strength connecting bolts is increasing year by year. Bolt breakage can cause damage to components at the least, such as secondary damage caused by bolt breakage and falling, which will result in high maintenance costs, and serious consequences such as blade falling and unit collapse.

[0003] At present, there is no effective and economical online monitoring method in the wind power industry, which can accurately diagnose and give predictive maintenance suggestions. On the one hand, the failure modes of high-strength connecting bolts are diverse and complex, and a single monitoring method cannot fully identify multiple modes of failure; on the other hand, there are many bolts in the entire unit, and it is difficult to install and arrange monitoring equipment such as sensors to locate the faulty bolts. In addition, the sensors need to be calibrated regularly, which is costly. At present, the maintenance of bolts is still mainly based on regular maintenance and post-maintenance. Generally, manpower is arranged for regular inspections, and then the bolts are visually inspected one by one or a handheld ultrasonic flaw detector is used to identify fractures, looseness and other faults.

[0004] Therefore, in order to ensure the safe and healthy operation of wind turbines, reduce operation and maintenance costs, avoid major safety accidents and major economic losses of equipment, and the adverse effects caused by major safety accidents, how to pre-alarm high-strength bolt failures of blades, towers and other components, prevent accidents and prepare spare parts in advance for maintenance and replacement is an issue that the industry urgently needs to solve. Summary of the invention

[0005] In view of this, the purpose of this application is to provide a method, device, equipment and medium for monitoring high-strength bolt faults of wind turbines, which can quickly and accurately identify and precisely locate various bolt faults. The specific scheme is as follows:

[0006] In a first aspect, the present application discloses a method for monitoring high-strength bolt failures of a wind turbine generator set, comprising:

[0007] Determine the target high-strength bolts to be monitored in the target components of the wind turbine;

[0008] The impact and stress impact and bolt loosening angle change generated by the target high-strength bolt are detected by an impact and angle composite sensor pre-installed on the target high-strength bolt to obtain a plurality of feature information, and the plurality of feature information are feature extracted to obtain initial feature data;

[0009] Preprocessing the initial feature data to obtain target feature data;

[0010] A comprehensive decision is made based on the target characteristic data whether the target high-strength bolt has a fault and the corresponding fault mode and fault location.

[0011] Optionally, different impact and angle composite sensors are connected in series via high-strength adapter wires to monitor relative looseness between the nut and the screw and / or screw breakage and / or looseness failure.

[0012] Optionally, the wind turbine high-strength bolt fault monitoring method further includes:

[0013] By analyzing the failure mechanism of all high-strength bolts in the target component of the wind turbine generator set, the target high-strength bolt to be monitored is determined from all the high-strength bolts;

[0014] Uniquely encoding the impact and angle composite sensor to obtain an encoded sensor;

[0015] The encoded sensor is installed on the target high-strength bolt.

[0016] Optionally, the impact and stress impact generated by the target high-strength bolt are detected by an impact and angle composite sensor pre-installed on the target high-strength bolt to obtain a plurality of feature information, and feature extraction is performed on the plurality of feature information to obtain initial feature data, including:

[0017] The impact and stress impact generated by the target high-strength bolt are detected by an impact and angle composite sensor pre-installed on the target high-strength bolt to obtain an impact signal;

[0018] The impact signal is subjected to resonance demodulation, peak hold and A / D sampling processing in sequence to obtain a plurality of impact feature information, and feature extraction is performed on the plurality of impact feature information to obtain initial impact feature data.

[0019] Optionally, detecting the bolt loosening angle change of the target high-strength bolt by using an impact and angle composite sensor pre-installed on the target high-strength bolt to obtain a plurality of feature information, and extracting features from the plurality of feature information to obtain initial feature data, including:

[0020] The bolt loosening angle change produced by the target high-strength bolt is detected by a sensitive device in an impact and angle composite sensor pre-installed on the target high-strength bolt to obtain an angle signal, and the angle signal is feature extracted to obtain initial angle feature data.

[0021] Optionally, the preprocessing the initial feature data to obtain target feature data includes:

[0022] The initial feature data is acquired through a preset diagnostic instrument, and abnormal data in the initial feature data is identified through the diagnostic instrument, and then the abnormal data is removed from the initial feature data to obtain target feature data.

[0023] Optionally, the comprehensively deciding whether the target high-strength bolt has a fault and the corresponding fault mode and fault location according to the target characteristic data includes:

[0024] The diagnostic instrument determines whether the target characteristic data satisfies the preset threshold conditions corresponding to the preset multiple fault modes. If so, it is determined that the target high-strength bolt is faulty, and the corresponding fault mode and fault location are determined; wherein the multiple fault modes include any one or more of the nut and screw relative looseness fault mode, screw tension looseness fault mode, screw crack and expansion fault mode, and bolt breakage and falling fault mode.

[0025] Optionally, the determining whether the target characteristic data satisfies preset threshold conditions corresponding to a plurality of preset failure modes, and if so, determining that the target high-strength bolt has a fault, includes:

[0026] Acquire the rotation angle of the delay line on the target high-strength bolt from the target characteristic data;

[0027] Determine whether the angle exceeds a preset angle threshold, and if so, determine whether the angle has a sudden change;

[0028] If the angle does not change suddenly, it is determined that the target high-strength bolt has a failure in the failure mode of relative looseness between the nut and the screw, and an alarm signal of relative looseness between the nut and the screw is generated.

[0029] Optionally, the determining whether the target characteristic data satisfies preset threshold conditions corresponding to a plurality of preset failure modes, and if so, determining that the target high-strength bolt has a fault, includes:

[0030] Acquire a frequency band corresponding to the opening and closing impact generated by the target high-strength bolt from the target characteristic data to obtain a first frequency band;

[0031] Resonantly demodulating the first frequency band and performing peak hold to obtain an opening and closing impact amplitude, and determining whether the opening and closing impact amplitude exceeds a preset opening and closing impact amplitude threshold;

[0032] If the opening and closing impact amplitude exceeds the opening and closing impact amplitude threshold, determining whether the opening and closing impact amplitude has a sudden change;

[0033] If the opening and closing impact amplitude does not change suddenly, it is determined that the target high-strength bolt has the screw rod tension loosening failure mode, and an alarm signal of screw rod tension loosening is generated.

[0034] Optionally, the determining whether the target characteristic data satisfies preset threshold conditions corresponding to a plurality of preset failure modes, and if so, determining that the target high-strength bolt has a fault, includes:

[0035] Acquire a frequency band corresponding to the stress impact generated by the target high-strength bolt from the target characteristic data to obtain a second frequency band;

[0036] Resonantly demodulating the second frequency band and performing peak hold to obtain a stress impact amplitude, and determining whether the stress impact amplitude exceeds a preset stress impact amplitude threshold;

[0037] If the stress impact amplitude exceeds the stress impact amplitude threshold, determining whether the stress impact amplitude has a sudden change;

[0038] If the stress impact amplitude does not change suddenly, it is determined that the target high-strength bolt has a failure mode in which cracks appear and expand in the screw rod, and an alarm signal of cracks appearing and expanding in the screw rod is generated.

[0039] Optionally, the determining whether the target characteristic data satisfies preset threshold conditions corresponding to a plurality of preset failure modes, and if so, determining that the target high-strength bolt has a fault, includes:

[0040] Acquire a frequency band corresponding to the impact shock generated by the target high-strength bolt from the target characteristic data to obtain a third frequency band;

[0041] Resonantly demodulating the third frequency band and performing peak hold to obtain a collision impact amplitude, and determining whether the collision impact amplitude exceeds a preset collision impact amplitude threshold;

[0042] If the impact amplitude exceeds the impact amplitude threshold, determining whether the angle undergoes a regular mutation;

[0043] If the angle undergoes a regular mutation, it is determined that the target high-strength bolt has a failure in the bolt breakage and falling failure mode, and an alarm signal of bolt breakage and falling is generated.

[0044] Optionally, after comprehensively determining whether the target high-strength bolt has a fault and the corresponding fault mode and fault location according to the target characteristic data, the method further includes:

[0045] If the target high-strength bolt has a fault, the corresponding fault mode and fault location are determined, and a corresponding alarm signal is generated according to the weight corresponding to the fault mode, and at the same time, the target characteristic data is screened according to the predetermined basic rules of decision data to obtain fault characteristic data;

[0046] The fault characteristic data and the corresponding fault mode and the fault location are packaged and sent to the target analysis software, so that the fault characteristic data and the corresponding fault mode and the fault location can be displayed in real time through the target analysis software, and the health assessment of the target high-strength bolt is performed based on the acquired data to generate corresponding actual operation and maintenance suggestions.

[0047] In a second aspect, the present application discloses a high-strength bolt fault monitoring device for a wind turbine, including an impact and angle composite sensor and a diagnostic instrument;

[0048] The impact and angle composite sensor specifically includes: a detection module, which is used to detect the impact and stress impact and bolt loosening angle change generated by the target high-strength bolt to be monitored in the target component of the wind turbine to obtain multiple feature information, and extract features from the multiple feature information to obtain initial feature data; a data preprocessing module, which is used to preprocess the initial feature data to obtain target feature data; the impact and angle composite sensor is pre-installed on the target high-strength bolt;

[0049] The diagnostic instrument specifically includes: a comprehensive decision module, which is used to comprehensively decide whether the target high-strength bolt has a fault and the corresponding fault mode and fault location based on the target characteristic data.

[0050] In a third aspect, the present application discloses an electronic device, comprising a processor and a memory; wherein the processor implements the aforementioned method for monitoring high-strength bolt faults of wind turbines when executing a computer program stored in the memory.

[0051] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned method for monitoring high-strength bolt faults of a wind turbine is implemented.

[0052] It can be seen that the present application first determines the target high-strength bolts to be monitored in the target components of the wind turbine, and then detects the impact and stress impact and bolt loosening angle change generated by the target high-strength bolts through the impact and angle composite sensor pre-installed on the target high-strength bolts to obtain multiple feature information, and extracts features from the multiple feature information to obtain initial feature data, and then pre-processes the initial feature data to obtain target feature data, and finally comprehensively decides whether the target high-strength bolt has a fault and the corresponding fault mode and fault location based on the target feature data. The present application can extract features of the impact and angle change of the bolts through the impact and angle composite sensor installed in the bolt fault-prone area, and can achieve accurate identification and precise positioning of various bolt faults through comprehensive analysis of the feature extracted data. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0054] Figure 1 A flow chart of a method for monitoring high-strength bolt failures of a wind turbine disclosed in the present application;

[0055] Figure 2 A schematic diagram of a specific wind turbine blade monitoring area disclosed in the present application;

[0056] Figure 3 A flow chart of a specific method for monitoring high-strength bolt faults of wind turbines disclosed in this application;

[0057] Figure 4 A schematic diagram of a specific impact and angle composite sensor structure disclosed in this application;

[0058] Figure 5 A schematic diagram of a specific impact detection circuit structure disclosed in this application;

[0059] Figure 6 A schematic diagram of a specific angle detection circuit structure disclosed in this application;

[0060] Figure 7 A specific wind turbine high-strength bolt fault monitoring system framework disclosed in this application;

[0061] Figure 8 This is a schematic structural diagram of a high-strength bolt fault monitoring device for a wind turbine disclosed in the present application;

[0062] Fig. 9 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0064] The present application discloses a method for monitoring high-strength bolt failures in a wind turbine generator system. Figure 1 As shown, the method includes:

[0065] Step S11: determining the target high-strength bolts to be monitored in the target components of the wind turbine generator system.

[0066] In this embodiment, it is first necessary to determine the target high-strength bolts that need to be monitored based on the failure mechanism analysis of the high-strength bolts in the target components of the wind turbine, that is, it is not necessary to monitor all the high-strength bolts in the target components, but only to monitor some of the high-strength bolts in the target components; wherein the target components include but are not limited to blades, gear boxes, generators, etc. For example, see Figure 2 As shown, when determining the high-strength bolts to be monitored in the wind turbine blades, considering that the fracture and loosening failures of the high-strength bolts in the blades are mainly concentrated in the fatigue affected area of ​​the blades, only the high-strength bolts in the fatigue affected area of ​​the blades can be monitored.

[0067] Step S12: Detect the impact and stress impact and bolt loosening angle change generated by the target high-strength bolt through an impact and angle composite sensor pre-installed on the target high-strength bolt to obtain multiple feature information, and extract features from the multiple feature information to obtain initial feature data.

[0068] In this embodiment, after determining the target high-strength bolt to be monitored in the target component of the wind turbine, the impact and stress impact and bolt loosening angle change generated by the target high-strength bolt under the action of force can be collected by the impact and angle composite sensor pre-installed on the target high-strength bolt to obtain corresponding impact signals and angle signals, and then the impact signals and the angle signals are processed accordingly to obtain multiple feature information, and then the multiple feature information is extracted to obtain initial feature data. It should be pointed out that in order to prevent the high-strength bolt from falling into the wheel hub when it breaks and causing secondary damage to other components, different impact and angle composite sensors can be connected in series by using a Teflon high-strength wire adapter to monitor the relative looseness of the nut and the screw and / or the screw breakage and / or looseness fault, such as when the nut and the screw are not relatively loose, the screw is stretched, causing looseness with the fastening object, etc. The impact and angle composite can be a sensor formed by a combination of an impact sensor and an angle sensor, or a single sensor that can simultaneously detect impact and angle to obtain multiple physical quantities.

[0069] In this embodiment, the method for monitoring the failure of high-strength bolts of a wind turbine generator set specifically further includes: analyzing the failure mechanism of all high-strength bolts in the target component of the wind turbine generator set, and determining the target high-strength bolt to be monitored from all the high-strength bolts; uniquely encoding the impact and angle composite sensor to obtain the encoded sensor; and installing the encoded sensor on the target high-strength bolt. In this embodiment, the failure mechanism of all high-strength bolts in the target component of the wind turbine generator set can be first analyzed, and then the target high-strength bolt to be monitored can be determined from all the high-strength bolts, and then the impact and angle composite sensor can be encoded so that each of the impact and angle composite sensor has a unique code, thereby obtaining the encoded sensor, and then the encoded sensor can be installed on the target high-strength bolt. When a certain target high-strength bolt fails, the specific location of the failure can be determined by the unique code corresponding to the impact and angle composite sensor installed on the target high-strength bolt.

[0070] Step S13: pre-processing the initial feature data to obtain target feature data.

[0071] In this embodiment, after extracting the features of the plurality of feature information to obtain the initial feature data, the obtained initial feature data may be subjected to corresponding preprocessing operations to obtain the target feature data. For example, the abnormal data in the initial feature data may be removed, and then the removed initial feature data may be subjected to feature screening, and the screened feature data may be used as the target feature data.

[0072] Step S14: comprehensively determine whether the target high-strength bolt has a fault and the corresponding fault mode and fault location based on the target characteristic data.

[0073] In this embodiment, after the initial characteristic data is preprocessed to obtain the target characteristic data, it is possible to determine whether the target high-strength bolt has a fault and the specific fault mode when a fault occurs through the threshold conditions corresponding to the target characteristic data and the preset multiple fault modes, and the specific location of the faults such as bolt stretching, bolt cracking, bolt breakage, and relative looseness of the nut and the screw can also be determined through the unique code corresponding to the target high-strength bolt.

[0074] In this embodiment, after making a comprehensive decision based on the target characteristic data as to whether the target high-strength bolt has a fault and the corresponding fault mode and fault location, it specifically also includes: if the target high-strength bolt has a fault, determining the corresponding fault mode and fault location, and generating a corresponding alarm signal according to the weight corresponding to the fault mode, and at the same time screening the target characteristic data according to a predetermined basic rule of decision data to obtain fault characteristic data; packaging the fault characteristic data and the corresponding fault mode and fault location and sending them to the target analysis software, so that the fault characteristic data and the corresponding fault mode and fault location can be displayed in real time through the target analysis software, and performing a health assessment on the target high-strength bolt based on the acquired data to generate corresponding actual operation and maintenance suggestions. It can be understood that if the above-mentioned target high-strength bolt has faults such as breakage and / or loosening, the specific location and specific fault mode of the fault can be further determined, and a corresponding pre-alarm signal can be generated according to the weights pre-configured for the fault mode. This is because different fault modes are interrelated. For example, due to external forces such as alternating loads and ambient temperature, the screw is stretched. When the nut and the screw are not relatively loose, the looseness caused by the fastening object will cause cracks in the screw under the action of repeated alternating loads. Further expansion of the cracks may cause the bolt to break and fall off. Therefore, different weight values ​​can be set for different fault modes, so that the generated alarm signal can accurately display the specific state of the current fault, that is, it can reflect the severity of the fault. At the same time, the target characteristic data is screened according to the predetermined basic rules of decision data to obtain fault characteristic data, that is, the characteristic data of the specific fault mode is screened from the target characteristic data according to the predetermined basic rules of decision data, and the fault characteristic data and the corresponding fault mode and the fault position are packaged and sent to the target analysis software, and then the fault characteristic data and the corresponding specific fault mode and the specific fault position are presented through the target analysis software, so as to provide specific fault information to the user, and the target analysis software can also evaluate the health status of the target high-strength bolt based on the acquired fault characteristic data and the corresponding fault mode and the fault position, and then generate suggestions that the user can implement for operation and maintenance, such as generating an operation and maintenance suggestion for replacing the target high-strength bolt with a bolt breakage and falling off failure mode. It can be understood that after the user performs corresponding operation and maintenance operations on the target high-strength bolt, such as replacing the target high-strength bolt with a cracked screw, the impact and angle composite sensor can continue to monitor the target high-strength bolt to obtain a new detection result. If the new result shows that the current target high-strength bolt has no fault, it indicates that the current target high-strength bolt is in a healthy state. In a specific implementation, the target analysis software may specifically be cloud platform analysis software.

[0075] It can be seen that the embodiment of the present application first determines the target high-strength bolt to be monitored in the target component of the wind turbine, and then detects the impact and stress impact and bolt loosening angle change generated by the target high-strength bolt through the impact and angle composite sensor pre-installed on the target high-strength bolt, obtains multiple feature information, and extracts features from the multiple feature information to obtain initial feature data, and then pre-processes the initial feature data to obtain target feature data, and finally comprehensively decides whether the target high-strength bolt has a fault and the corresponding fault mode and fault location based on the target feature data. It can be seen that the embodiment of the present application can extract features of the impact and angle change of the bolt through the impact and angle composite sensor installed in the bolt fault-prone area, and can achieve accurate identification and precise positioning of various bolt faults through comprehensive analysis of the feature extracted data.

[0076] The present application discloses a specific method for monitoring high-strength bolt failures in a wind turbine generator system. Figure 3 As shown, the method includes:

[0077] Step S21: determining a target high-strength bolt to be monitored in a target component of a wind turbine generator system.

[0078] Step S22: detecting the impact and stress impact generated by the target high-strength bolt through an impact and angle composite sensor pre-installed on the target high-strength bolt to obtain an impact signal.

[0079] In this embodiment, after determining the target high-strength bolt to be monitored in the target component of the wind turbine generator set, the impact impact and / or stress impact received by the target high-strength bolt can be detected by using an impact and angle composite sensor pre-installed on the target high-strength bolt, that is, the bolt stretching, bolt crack and bolt breakage failures received by the target high-strength bolt can be detected to obtain a corresponding impact signal.

[0080] In a specific embodiment, see Figure 4 As shown, Figure 4 The circuit structure of a specific impact and angle composite sensor is shown, including a power supply circuit, an impact sensitive device, an impact detection circuit, a single chip microcomputer, a TMR (Tunnel Magneto Resistance) magnetoresistive sensor, an interface circuit and a connector or cable. The structure of the impact detection circuit is shown in FIG. Figure 5 As shown, Figure 5The impact detection circuit shown converts the charge signal of the impact sensitive device into a voltage signal collected by the single-chip AD (i.e., the conversion of analog signal and digital signal). The circuit specifically includes an impact sensitive device, a charge amplifier, a resonant demodulation circuit, a peak holding circuit and a single-chip circuit.

[0081] Step S23: performing resonance demodulation, peak hold and A / D sampling processing on the impact signal in sequence to obtain a plurality of impact feature information, and performing feature extraction on the plurality of impact feature information to obtain initial impact feature data.

[0082] In this embodiment, the impact and stress impact generated by the target high-strength bolt are detected by an impact and angle composite sensor pre-installed on the target high-strength bolt. After the impact signal is obtained, the above impact signal is resonantly demodulated and peak held, and then A / D sampling processing is performed to obtain corresponding multiple impact feature information, and then feature extraction is performed on the above multiple impact feature information to obtain initial impact feature data.

[0083] Step S24: detecting the bolt loosening angle change of the target high-strength bolt by means of a sensitive device in an impact and angle composite sensor pre-installed on the target high-strength bolt to obtain an angle signal, and extracting features from the angle signal to obtain initial angle feature data.

[0084] In this embodiment, after extracting the characteristics of the multiple impact characteristic information to obtain the initial impact characteristic data, the loosening angle change of the target high-strength bolt can be further detected by using a sensitive device in the impact and angle composite sensor pre-installed on the target high-strength bolt, specifically a device sensitive to angle change (such as a TMR magnetoresistive sensor), to obtain an angle signal, and then extract the characteristics of the angle signal to obtain the initial angle characteristic data. For details, see Figure 6 As shown, Figure 6 A specific angle detection circuit structure is shown. Figure 6 The angle detection circuit in the device transmits the angle change information detected by the TMR magnetoresistive sensor to the microcontroller through the SPI (Serial Peripheral interface), and the data is output through the interface circuit after being processed by the microcontroller.

[0085] Step S25: Acquire the initial impact characteristic data and the initial angle characteristic data through a preset diagnostic instrument, identify abnormal data in the initial impact characteristic data and the initial angle characteristic data through the diagnostic instrument, and then remove the abnormal data from the initial impact characteristic data and the initial angle characteristic data to obtain target characteristic data.

[0086] In this embodiment, after feature extraction is performed on the angle signal to obtain the initial angle feature data, the initial impact feature data and the initial angle feature data can be obtained through a preset diagnostic instrument, and then the diagnostic instrument can be used to identify abnormal data in the initial impact feature data and the initial angle feature data, for example, values ​​exceeding 360 degrees in the initial angle feature data and data with impact SV values ​​exceeding 5000SV in the initial impact feature data are taken as abnormal data, and the identified abnormal data are eliminated from the initial impact feature data and the initial angle feature data to obtain target feature data.

[0087] Step S26: The diagnostic instrument determines whether the target characteristic data satisfies the preset threshold conditions corresponding to the preset multiple fault modes. If so, it is determined that the target high-strength bolt is faulty, and the corresponding fault mode and fault location are determined; wherein the multiple fault modes include any one or more of a relative looseness fault mode between the nut and the screw, a looseness fault mode due to tension of the screw, a crack in the screw and its expansion fault mode, and a bolt breakage and falling fault mode.

[0088] In this embodiment, after the abnormal data is eliminated from the initial impact characteristic data and the initial angle characteristic data to obtain the target characteristic data, the above-mentioned diagnostic instrument can further determine whether the target characteristic data satisfies the preset threshold conditions corresponding to the preset multiple fault modes. If the preset threshold conditions are met, it is determined that the above-mentioned target high-strength bolt has faults such as breakage and / or loosening, and the specific fault mode and the location of the fault can be determined; wherein, the multiple fault modes include any one or more of the relative looseness fault mode of the nut and the screw, the looseness fault mode of the screw through stretching, the crack and expansion fault mode of the screw, and the breakage and falling fault mode of the bolt.

[0089] In a first specific implementation, the determination of whether the target characteristic data satisfies the preset threshold conditions corresponding to the preset multiple fault modes, and if so, determining that the target high-strength bolt has a fault, can specifically include: obtaining the rotation angle of the retardation line on the target high-strength bolt from the target characteristic data; determining whether the angle exceeds the preset angle threshold, and if so, determining whether the angle has a sudden change; if the angle has not changed suddenly, determining that the target high-strength bolt has a fault in the nut and screw relative looseness fault mode, and generating an alarm signal of the nut and screw relative looseness. For example, when the nut and the screw are relatively loose, an angle will be generated based on the forward or reverse rotation of the retarder, so the rotation angle of the retarder can be monitored, and when the above-mentioned monitored angle exceeds the preset angle threshold, such as when the above-mentioned angle exceeds 10 degrees, it can be determined that the target high-strength bolt has a nut and screw relative looseness fault, and a corresponding nut and screw relative looseness alarm signal is generated when the above-mentioned angle information is determined to be accurate and the angle has no sudden change.

[0090] In a second specific implementation manner, the determination of whether the target characteristic data satisfies preset threshold conditions corresponding to a plurality of preset fault modes, and if so, determining that the target high-strength bolt has a fault, may specifically include: obtaining a frequency band corresponding to the opening and closing impact generated by the target high-strength bolt from the target characteristic data to obtain a first frequency band; resonantly demodulating the first frequency band and performing peak hold to obtain an opening and closing impact amplitude, and determining whether the opening and closing impact amplitude exceeds a preset opening and closing impact amplitude threshold; if the opening and closing impact amplitude exceeds the opening and closing impact amplitude threshold, determining whether a sudden change occurs in the opening and closing impact amplitude; if the opening and closing impact amplitude does not suddenly change, determining that the target high-strength bolt has a fault in the screw rod tension loosening failure mode, and generating an alarm signal for screw rod tension loosening. For example, when there is no relative looseness between the nut and the screw but the screw is stretched, the flange surface connected by the bolt or bolt gasket will open on the stress surface, and will generate impact opening and closing shock under alternating load. The impact opening and closing shock is a frequency band. The impact opening and closing shock amplitude is obtained by resonant demodulation of the frequency band and peak holding. When the amplitude exceeds the preset impact opening and closing shock amplitude threshold, such as when the amplitude exceeds 800SV, it can be determined that the target high-strength bolt has a screw loosening fault, and a corresponding screw loosening alarm signal is generated.

[0091] In a third specific implementation manner, the determining whether the target characteristic data satisfies preset threshold conditions corresponding to a plurality of preset fault modes, and if so, determining that the target high-strength bolt has a fault, may specifically include: obtaining a frequency band corresponding to the stress shock generated by the target high-strength bolt from the target characteristic data to obtain a second frequency band; resonantly demodulating the second frequency band and performing peak hold to obtain a stress shock amplitude, and determining whether the stress shock amplitude exceeds a preset stress shock amplitude threshold; if the stress shock amplitude exceeds the stress shock amplitude threshold, determining whether a sudden change occurs in the stress shock amplitude; if the stress shock amplitude does not suddenly change, determining that the target high-strength bolt has a fault in the screw rod cracking and extending failure mode, and generating an alarm signal of screw rod cracking and extending. It can be understood that when cracks appear in the screw and expand, the natural frequency of the bolt will decrease and stress shock will be generated. The stress shock is a frequency band. The corresponding stress shock amplitude is obtained by resonant demodulation of the frequency band and peak holding. When the stress shock amplitude exceeds the preset stress shock amplitude threshold, such as the stress shock amplitude exceeds 500SV, and there is no sudden change, it can be determined that the target high-strength bolt has a screw crack and expansion fault, and a corresponding screw crack and expansion alarm signal is generated.

[0092] In a fourth specific implementation, the determining whether the target characteristic data satisfies preset threshold conditions corresponding to a plurality of preset fault modes, and if so, determining that the target high-strength bolt has a fault, comprises: obtaining a frequency band corresponding to the impact shock generated by the target high-strength bolt from the target characteristic data to obtain a third frequency band; resonantly demodulating the third frequency band and performing peak hold to obtain an impact shock amplitude, and determining whether the impact shock amplitude exceeds a preset impact shock amplitude threshold; if the impact shock amplitude exceeds the impact shock amplitude threshold, determining whether the angle undergoes regular mutations; if the angle undergoes regular mutations, determining that the target high-strength bolt has a fault in the bolt breakage and falling failure mode, and generating an alarm signal for bolt breakage and falling. It can be understood that when the bolt breaks and falls, the impact and angle composite sensor is hung near the bolt hole by the high-strength adapter wire. As the wheel hub rotates, high-amplitude, multi-frequency irregular impact shocks will be generated and the angle will show regular mutation outputs. The impact shock is a frequency band, and the impact shock amplitude is obtained by resonant demodulation of the frequency band and peak holding. When the above-mentioned impact shock amplitude exceeds the preset impact shock amplitude threshold, such as when the impact shock amplitude exceeds 800SV, it is determined that the target high-strength bolt has a bolt breakage and falling fault, and a corresponding bolt breakage and falling alarm signal is generated.

[0093] For further information, see Figure 7 As stated, Figure 7 A specific framework of a high-strength bolt fault monitoring system for a wind turbine is shown, including: an impact and angle composite sensor, a diagnostic instrument and a cloud platform analysis software; wherein the structure of the impact and angle composite sensor includes: a power processing module, an impact resonance demodulation peak holding module, an angle signal detection module and a single-chip computer and communication module; the diagnostic instrument includes a data preprocessing module, a comprehensive decision-making module, a pre-alarm module, a data screening module and a data storage module; the cloud platform analysis software includes a bolt detection data presentation and status evaluation module and an operation and maintenance suggestion issuance and operation and maintenance implementation feedback module. The specific processing flow is as follows: first, based on the fault mechanism analysis, the specific bolts to be monitored are determined, and the impact and angle composite sensors are installed on the determined bolts to be monitored. Then, each of the impact and angle composite sensors is uniquely encoded, and then the impact and angle composite sensors are used to perform impact and stress impact detection and feature extraction, angle signal detection and feature extraction on the four fault modes caused by the high-strength connecting bolts of the wind turbine. Then, the extracted features are screened and the screened feature data is sent to the diagnostic instrument. After the diagnostic instrument obtains the feature data sent by the impact and angle composite sensor, the feature data is preprocessed through the data preprocessing module, outlier identification and elimination are performed, and accurate feature data is provided for comprehensive decision-making. Then, the feature data after eliminating outliers is sent to the comprehensive decision-making module. The comprehensive decision-making module and the The diagnostic instrument is connected to the pre-alarm module, which is specifically used to make a fusion decision based on the monitored high-strength connecting bolt position coding information and the characteristic information of the four fault modes of the high-strength connecting bolts, to perform special fault positioning and give a pre-alarm of the specific fault type; the diagnostic instrument can also further screen the characteristic data, position coding data, comprehensive decision-making process and conclusion data basic rules, and then package and upload them to the cloud platform wirelessly, and then present the characteristic data and decision conclusions issued by the diagnostic instrument in real time through the cloud platform analysis software, and at the same time, based on the characteristic data and decision conclusions, the health of the four fault modes of the high-strength bolts is evaluated and operation and maintenance suggestions are given, and specific implementation of operation and maintenance operations is issued according to the operation and maintenance suggestions and the operation and maintenance feedback results are obtained. The alarm frequency, the weighting of the four fault modes and the operation and maintenance suggestions can also be adjusted according to application experience to meet the personalized needs of users.

[0094] It should be pointed out that the judgment of whether the target high-strength bolt has a fault and the corresponding fault mode is determined by making a comprehensive decision on the target feature data obtained by the diagnostic instrument after feature extraction of the impact signal and angle signal collected by the impact and angle composite sensor. For example, by extracting and analyzing the features of the impact signal sensitive to the impact and angle composite sensor, the diagnostic instrument can identify whether the bolt has a loose bolt and fastening object, a screw crack, or other faults; by extracting and analyzing the features of the angle signal sensitive to the impact and angle composite sensor, the diagnostic instrument can identify whether the bolt has a relative loose nut and screw fault; by comprehensively processing and analyzing the impact signal and angle signal sensitive to the impact and angle composite sensor, the diagnostic instrument can identify whether the bolt has a bolt breakage and falling fault. By performing composite monitoring of the impact signal and angle signal, suggestions can be given for comprehensive decision-making and predictive maintenance.

[0095] For a more specific processing procedure of the above step S21, reference may be made to the corresponding contents disclosed in the above embodiments, which will not be described in detail here.

[0096] It can be seen that the embodiment of the present application detects the impact and stress impact generated by the target high-strength bolt through the impact and angle composite sensor pre-installed on the target high-strength bolt to obtain an impact signal, and then detects the bolt loosening angle change generated by the target high-strength bolt through the sensitive device in the impact and angle composite sensor pre-installed on the target high-strength bolt to obtain an angle signal, and then performs feature extraction on the impact signal and the angle signal to obtain target feature data, and sends the target feature data to the diagnostic instrument. The diagnostic instrument can detect the relative looseness failure mode of the nut and the screw, the tensile loosening failure mode of the screw, the crack and expansion failure mode of the screw, and the bolt breakage and falling failure mode. The embodiment of the present application can detect the impact and stress impact and bolt loosening angle change generated by the target high-strength bolt by directly adding a low-cost and easy-to-install and debug impact and angle composite sensor on the bolts in the areas prone to bolt breakage, loosening, etc., and obtain corresponding impact signals and angle signals. Then, through the diagnostic instrument, feature extraction and comprehensive decision-making can be performed to accurately identify the four types of faults: relative looseness failure mode of nut and screw, tensile looseness failure mode of screw, crack and expansion failure mode of screw, and bolt breakage and falling failure mode, and determine the specific fault location.

[0097] Correspondingly, the present application also discloses a wind turbine high-strength bolt fault monitoring device, see Figure 8 As shown, the device includes an impact and angle composite sensor 11 and a diagnostic instrument 12;

[0098] The impact and angle composite sensor 11 specifically includes: a detection module, which is used to detect the impact and stress impact and bolt loosening angle change generated by the target high-strength bolt to be monitored in the target component of the wind turbine to obtain multiple feature information, and extract features from the multiple feature information to obtain initial feature data; a data preprocessing module, which is used to preprocess the initial feature data to obtain target feature data; the impact and angle composite sensor is pre-installed on the target high-strength bolt;

[0099] The diagnostic instrument 12 specifically includes: a comprehensive decision module, which is used to comprehensively decide whether the target high-strength bolt has a fault and the corresponding fault mode and fault location based on the target characteristic data.

[0100] Among them, the specific working processes of the above-mentioned modules can refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0101] It can be seen that in the embodiment of the present application, the target high-strength bolt to be monitored in the target component of the wind turbine is first determined, and then the impact and stress impact and bolt loosening angle change generated by the target high-strength bolt are detected by the impact and angle composite sensor pre-installed on the target high-strength bolt to obtain multiple feature information, and the multiple feature information is feature extracted to obtain initial feature data, and then the initial feature data is pre-processed to obtain target feature data, and finally, a comprehensive decision is made based on the target feature data whether the target high-strength bolt has a fault and the corresponding fault mode and fault location. It can be seen that the embodiment of the present application can extract features of the impact and angle change of the bolt through the impact and angle composite sensor installed in the bolt fault-prone area, and through comprehensive analysis of the feature extracted data, it can achieve accurate identification and precise positioning of various bolt faults.

[0102] In some specific embodiments, different impact and angle composite sensors are connected in series via high-strength adapter wires to monitor relative looseness between the nut and the screw and / or screw breakage and / or looseness failure.

[0103] In some specific embodiments, the detection module may specifically include:

[0104] An impact detection unit, used to detect the impact and stress impact generated by the target high-strength bolt through an impact and angle composite sensor pre-installed on the target high-strength bolt to obtain an impact signal;

[0105] The first feature extraction unit is used to perform resonance demodulation, peak hold and A / D sampling processing on the impact signal in sequence to obtain a plurality of impact feature information, and perform feature extraction on the plurality of impact feature information to obtain initial impact feature data.

[0106] In some specific embodiments, the detection module may specifically include:

[0107] An angle detection unit, used to detect the bolt loosening angle change generated by the target high-strength bolt through a sensitive device in an impact and angle composite sensor pre-installed on the target high-strength bolt, and obtain an angle signal;

[0108] The second feature extraction unit is used to extract features from the angle signal to obtain initial angle feature data.

[0109] In some specific embodiments, the data preprocessing module may specifically include:

[0110] an abnormal data identification unit, used for acquiring the initial characteristic data through a preset diagnostic instrument, and identifying abnormal data in the initial characteristic data through the diagnostic instrument;

[0111] The abnormal data elimination unit is used to eliminate the abnormal data from the initial feature data to obtain target feature data.

[0112] In some specific embodiments, the comprehensive decision module may specifically include:

[0113] A first judgment unit, used to judge whether the target characteristic data satisfies preset threshold conditions corresponding to multiple preset fault modes through the diagnostic instrument;

[0114] A fault determination module is used to determine that the target high-strength bolt has a fault if the target characteristic data satisfies the preset threshold conditions corresponding to the preset multiple fault modes, and to determine the corresponding fault mode and fault location; wherein the multiple fault modes include any one or more of a relative looseness fault mode between the nut and the screw, a looseness fault mode due to tension of the screw, a crack in the screw and its expansion fault mode, and a bolt breakage and falling fault mode.

[0115] In some specific embodiments, the fault determination module may specifically include:

[0116] An angle information acquisition unit, used to acquire the rotation angle of the delay line on the target high-strength bolt from the target characteristic data;

[0117] A second judgment unit, used to judge whether the angle exceeds a preset angle threshold;

[0118] a third judging unit, configured to judge whether the angle changes suddenly if the angle exceeds the angle threshold;

[0119] The first fault mode determination unit is used to determine that the target high-strength bolt has a fault in the relative looseness fault mode of the nut and the screw rod if the angle does not change suddenly, and generate an alarm signal of the relative looseness of the nut and the screw rod.

[0120] In some specific embodiments, the fault determination module may specifically include:

[0121] A first frequency band acquisition unit, configured to acquire a frequency band corresponding to the opening and closing impact generated by the target high-strength bolt from the target characteristic data to obtain a first frequency band;

[0122] A first data processing unit is used to resonate demodulate the first frequency band and hold the peak value to obtain the opening and closing impact amplitude;

[0123] A fourth judgment unit, used to judge whether the opening and closing impact amplitude exceeds a preset opening and closing impact amplitude threshold;

[0124] a fifth judgment unit, configured to judge whether a sudden change occurs in the opening and closing impact amplitude if the opening and closing impact amplitude exceeds the opening and closing impact amplitude threshold;

[0125] The second fault mode determination unit is used to determine that the target high-strength bolt has the screw rod tension loosening fault mode if the opening and closing impact amplitude does not change suddenly, and generate an alarm signal of screw rod tension loosening.

[0126] In some specific embodiments, the fault determination module may specifically include:

[0127] A second frequency band acquisition unit, configured to acquire a frequency band corresponding to the stress impact generated by the target high-strength bolt from the target characteristic data to obtain a second frequency band;

[0128] A second data processing unit is used to perform resonance demodulation and peak hold on the second frequency band to obtain a stress impact amplitude;

[0129] a sixth judging unit, configured to judge whether the stress impact amplitude exceeds a preset stress impact amplitude threshold;

[0130] a seventh judgment unit, configured to judge whether a sudden change occurs in the stress impact amplitude if the stress impact amplitude exceeds the stress impact amplitude threshold;

[0131] The third fault mode determination unit is used to determine that the target high-strength bolt has a fault mode in which cracks appear and expand in the screw rod if the stress impact amplitude does not change suddenly, and to generate an alarm signal of cracks appearing and expanding in the screw rod.

[0132] In some specific embodiments, the fault determination module may specifically include:

[0133] A third frequency band acquisition unit, configured to acquire a frequency band corresponding to the impact shock generated by the target high-strength bolt from the target characteristic data, to obtain a third frequency band;

[0134] A third data processing unit is used to perform resonance demodulation and peak hold on the third frequency band to obtain an impact amplitude;

[0135] an eighth judgment unit, configured to judge whether the impact amplitude exceeds a preset impact amplitude threshold;

[0136] a ninth judgment unit, configured to judge whether a regular mutation occurs to the angle if the impact amplitude exceeds the impact amplitude threshold;

[0137] The fourth fault mode determination unit is used to determine that the target high-strength bolt has a fault of the bolt breakage and falling failure mode if the angle undergoes regular mutations, and to generate an alarm signal of bolt breakage and falling.

[0138] In some specific embodiments, after the comprehensive decision module, the following may also be included:

[0139] a fault mode determination unit, configured to determine a corresponding fault mode and a fault location if the target high-strength bolt has a fault;

[0140] An alarm signal generating unit, used to generate a corresponding alarm signal according to the weight corresponding to the fault mode;

[0141] A data screening unit, used to screen the target characteristic data according to a predetermined basic rule of decision data to obtain fault characteristic data;

[0142] A data sending unit, used for packaging the fault characteristic data and the corresponding fault mode and fault location and sending them to target analysis software;

[0143] A data display unit is used to display the fault characteristic data and the corresponding fault mode and fault location in real time through the target analysis software, and to perform a health assessment on the target high-strength bolt based on the acquired data to generate corresponding actual operation and maintenance suggestions.

[0144] Furthermore, the present application also discloses an electronic device. Fig. 9 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0145] Fig. 9 A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the method for monitoring the high-strength bolt fault of a wind turbine set disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0146] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0147] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0148] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, which can be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the wind turbine high-strength bolt fault monitoring method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include computer programs that can be used to complete other specific tasks.

[0149] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the above-disclosed method for monitoring high-strength bolt faults of wind turbines is implemented. The specific steps of the method can be referred to the corresponding contents disclosed in the above-disclosed embodiments, and will not be repeated here.

[0150] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0151] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0152] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0153] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0154] The above is a detailed introduction to a method, device, equipment and medium for monitoring high-strength bolt faults of wind turbines provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for monitoring high-strength bolt faults in a wind turbine generator system, characterized in that: include: Determine the target high-strength bolts to be monitored in the target components of the wind turbine; The impact and stress impact and bolt loosening angle change generated by the target high-strength bolt are detected by an impact and angle composite sensor pre-installed on the target high-strength bolt to obtain a plurality of characteristic information, and the plurality of characteristic information are feature extracted by a diagnostic instrument to obtain initial characteristic data, including: the impact and stress impact generated by the target high-strength bolt are detected by an impact and angle composite sensor pre-installed on the target high-strength bolt to obtain an impact signal; the impact signal is subjected to resonance demodulation, peak hold and A / D sampling processing in sequence to obtain a plurality of impact characteristic information, and the plurality of impact characteristic information are feature extracted by a diagnostic instrument to obtain initial impact characteristic data; the bolt loosening angle change generated by the target high-strength bolt is detected by a sensitive device in the impact and angle composite sensor pre-installed on the target high-strength bolt to obtain an angle signal, and the angle signal is feature extracted by a diagnostic instrument to obtain initial angle characteristic data; Preprocessing the initial feature data to obtain target feature data; Comprehensively determine whether the target high-strength bolt has a fault and the corresponding fault mode and fault location based on the target characteristic data; Wherein, different impact and angle composite sensors are connected in series by high-strength adapter wires to monitor the relative looseness between the nut and the screw and / or the breakage and / or looseness of the screw; The circuit structure of the impact and angle composite sensor includes a power supply circuit, an impact sensitive device, an impact detection circuit, a single chip microcomputer, a TMR magnetoresistive sensor, an interface circuit and a connector or a cable; wherein the impact detection circuit includes a charge amplifier, a resonance demodulation circuit and a peak holding circuit; Among them, the judgment of the screw tension loosening fault mode specifically includes: obtaining the frequency band corresponding to the opening and closing impact generated by the target high-strength bolt from the target characteristic data to obtain the first frequency band; resonant demodulation of the first frequency band and peak holding to obtain the opening and closing impact amplitude, and judging whether the opening and closing impact amplitude exceeds the preset opening and closing impact amplitude threshold; if the opening and closing impact amplitude exceeds the opening and closing impact amplitude threshold, judging whether the opening and closing impact amplitude has a sudden change; if the opening and closing impact amplitude has not a sudden change, judging that the target high-strength bolt has a fault in the screw tension loosening fault mode, and generating an alarm signal of screw tension loosening; Among them, the judgment of the failure mode of the screw rod cracking and expanding specifically includes: obtaining the frequency band corresponding to the stress impact generated by the target high-strength bolt from the target characteristic data to obtain the second frequency band; resonant demodulation and peak holding of the second frequency band to obtain the stress impact amplitude, and judging whether the stress impact amplitude exceeds the preset stress impact amplitude threshold; if the stress impact amplitude exceeds the stress impact amplitude threshold, judging whether the stress impact amplitude has a sudden change; if the stress impact amplitude has not a sudden change, judging that the target high-strength bolt has a failure mode of the screw rod cracking and expanding, and generating an alarm signal of the screw rod cracking and expanding; Among them, the judgment of the bolt breakage and falling failure mode specifically includes: obtaining the frequency band corresponding to the impact shock generated by the target high-strength bolt from the target characteristic data to obtain a third frequency band; resonantly demodulating the third frequency band and performing peak hold to obtain the impact shock amplitude, and judging whether the impact shock amplitude exceeds a preset impact shock amplitude threshold; if the impact shock amplitude exceeds the impact shock amplitude threshold, judging whether the angle undergoes regular mutations; if the angle undergoes regular mutations, judging that the target high-strength bolt has a fault in the bolt breakage and falling failure mode, and generating an alarm signal for bolt breakage and falling.

2. The method for monitoring high-strength bolt faults of a wind turbine generator set according to claim 1, characterized in that: Also includes: By analyzing the failure mechanism of all high-strength bolts in the target component of the wind turbine generator set, the target high-strength bolt to be monitored is determined from all the high-strength bolts; Uniquely encoding the impact and angle composite sensor to obtain an encoded sensor; The encoded sensor is installed on the target high-strength bolt.

3. The method for monitoring high-strength bolt failures of a wind turbine generator set according to claim 1, characterized in that: The preprocessing of the initial feature data to obtain target feature data includes: The initial feature data is acquired by the preset diagnostic instrument, and abnormal data in the initial feature data is identified by the diagnostic instrument, and then the abnormal data is removed from the initial feature data to obtain target feature data.

4. The method for monitoring high-strength bolt faults of a wind turbine generator set according to claim 1, characterized in that: The determining whether the target characteristic data satisfies preset threshold conditions corresponding to the preset multiple failure modes, and if so, determining that the target high-strength bolt has a fault, includes: Acquire the rotation angle of the delay line on the target high-strength bolt from the target characteristic data; Determine whether the angle exceeds a preset angle threshold, and if so, determine whether the angle has a sudden change; If the angle does not change suddenly, it is determined that the target high-strength bolt has a failure mode of relative looseness between the nut and the screw, and an alarm signal of relative looseness between the nut and the screw is generated.

5. The method for monitoring high-strength bolt failures of a wind turbine generator set according to any one of claims 1 to 4, characterized in that: After comprehensively determining whether the target high-strength bolt has a fault and the corresponding fault mode and fault location according to the target characteristic data, the method further includes: If the target high-strength bolt has a fault, the corresponding fault mode and fault location are determined, and a corresponding alarm signal is generated according to the weight corresponding to the fault mode, and at the same time, the target characteristic data is screened according to the predetermined basic rules of decision data to obtain fault characteristic data; The fault characteristic data and the corresponding fault mode and the fault location are packaged and sent to the target analysis software, so that the fault characteristic data and the corresponding fault mode and the fault location can be displayed in real time through the target analysis software, and the health assessment of the target high-strength bolt is performed based on the acquired data to generate corresponding actual operation and maintenance suggestions.

6. A high-strength bolt fault monitoring device for a wind turbine, characterized in that: Includes impact and angle composite sensors and diagnostic instruments; The impact and angle composite sensor specifically includes: a detection module, which is used to detect the impact and stress impact and bolt loosening angle change generated by the target high-strength bolt to be monitored in the target component of the wind turbine to obtain multiple feature information, and extract the features of the multiple feature information through a diagnostic instrument to obtain initial feature data; a data preprocessing module, which is used to preprocess the initial feature data to obtain target feature data; the impact and angle composite sensor is pre-installed on the target high-strength bolt; The diagnostic instrument specifically includes: a comprehensive decision module for comprehensively deciding whether the target high-strength bolt has a fault and the corresponding fault mode and fault location according to the target characteristic data; Wherein, different impact and angle composite sensors are connected in series by high-strength adapter wires to monitor the relative looseness between the nut and the screw and / or the breakage and / or looseness of the screw; The circuit structure of the impact and angle composite sensor includes a power supply circuit, an impact sensitive device, an impact detection circuit, a single chip microcomputer, a TMR magnetoresistive sensor, an interface circuit and a connector or a cable; wherein the impact detection circuit includes a charge amplifier, a resonance demodulation circuit and a peak holding circuit; The impact and stress impact and bolt loosening angle change generated by the target high-strength bolt are detected by the impact and angle composite sensor pre-installed on the target high-strength bolt to obtain multiple feature information, and the multiple feature information are feature extracted by the diagnostic instrument to obtain initial feature data, including: The detection module is specifically used to detect the impact and stress impact generated by the target high-strength bolt to obtain an impact signal; the impact signal is subjected to resonance demodulation, peak hold and A / D sampling processing in sequence to obtain multiple impact feature information; Accordingly, the diagnostic instrument is specifically used to: extract features from the plurality of impact feature information to obtain initial impact feature data; The detection module is specifically used to detect the bolt loosening angle change generated by the target high-strength bolt through the sensitive device in the impact and angle composite sensor pre-installed on the target high-strength bolt to obtain an angle signal; Accordingly, the diagnostic instrument is specifically used to: extract features from the angle signal to obtain initial angle feature data; Among them, the judgment of the screw tension loosening fault mode specifically includes: obtaining the frequency band corresponding to the opening and closing impact generated by the target high-strength bolt from the target characteristic data to obtain the first frequency band; resonant demodulation of the first frequency band and peak holding to obtain the opening and closing impact amplitude, and judging whether the opening and closing impact amplitude exceeds the preset opening and closing impact amplitude threshold; if the opening and closing impact amplitude exceeds the opening and closing impact amplitude threshold, judging whether the opening and closing impact amplitude has a sudden change; if the opening and closing impact amplitude has not a sudden change, judging that the target high-strength bolt has a fault in the screw tension loosening fault mode, and generating an alarm signal of screw tension loosening; Among them, the judgment of the failure mode of the screw rod cracking and expanding specifically includes: obtaining the frequency band corresponding to the stress impact generated by the target high-strength bolt from the target characteristic data to obtain the second frequency band; resonant demodulation and peak holding of the second frequency band to obtain the stress impact amplitude, and judging whether the stress impact amplitude exceeds the preset stress impact amplitude threshold; if the stress impact amplitude exceeds the stress impact amplitude threshold, judging whether the stress impact amplitude has a sudden change; if the stress impact amplitude has not a sudden change, judging that the target high-strength bolt has a failure mode of the screw rod cracking and expanding, and generating an alarm signal of the screw rod cracking and expanding; Among them, the judgment of the bolt breakage and falling failure mode specifically includes: obtaining the frequency band corresponding to the impact shock generated by the target high-strength bolt from the target characteristic data to obtain a third frequency band; resonantly demodulating the third frequency band and performing peak hold to obtain the impact shock amplitude, and judging whether the impact shock amplitude exceeds a preset impact shock amplitude threshold; if the impact shock amplitude exceeds the impact shock amplitude threshold, judging whether the angle undergoes regular mutations; if the angle undergoes regular mutations, judging that the target high-strength bolt has a fault in the bolt breakage and falling failure mode, and generating an alarm signal for bolt breakage and falling.

7. An electronic device, characterized in that: It comprises a processor and a memory; wherein, when the processor executes the computer program stored in the memory, the method for monitoring high-strength bolt faults of a wind turbine set as claimed in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, the method for monitoring high-strength bolt faults of a wind turbine set as described in any one of claims 1 to 5 is implemented.

Images