Vibrating wire sensor fault diagnosis and repair method, system and device and storage medium

Abstract

The invention discloses a vibrating wire sensor fault diagnosis and repair method, system and device, and a storage medium. The method comprises the steps of collecting an output signal of a vibrating wire sensor; amplitude values of all the collected output signals of the vibrating wire sensor are amplified, and a band-pass filter circuit is used for filtering; inputting the amplified and filtered data into a pre-constructed fault diagnosis and recognition model, and performing feature extraction and classification so as to recognize the vibrating wire sensor with the fault and the fault type of the vibrating wire sensor; according to the fault type, different modes are selected to repair the vibrating wire sensor with the fault; the diagnosis result and the working state of the fault diagnosis and recognition model and the real frequency of the repaired vibrating wire sensor are displayed; and storing all the data for subsequent analysis and iterative updating of a fault diagnosis and recognition model. According to the invention, fault diagnosis and online real-time monitoring can be accurately and effectively carried out on the vibrating wire sensor, and the vibrating wire sensor with faults can be rapidly repaired.

Description

Technical Field

[0001] The invention belongs to the field of fault diagnosis and repair of vibrating string sensors, and provides a method, system, device and storage medium for fault diagnosis and repair of vibrating string sensors. Background Art

[0002] During the operation of pumped storage power stations, vibrating string sensors are widely used to monitor the safety of their building structures. With the construction of pumped storage power stations such as Lianghekou, pumped storage power stations face challenges such as high altitude, large total installed capacity, and harsh operating environment. During the operation, vibrating string sensors are affected by harsh external conditions and their own characteristics, resulting in inaccurate frequency measurement, which affects the accuracy of stress measurement and poses certain risks to the safety monitoring of pumped storage power stations.

[0003] Starting from reducing the interference of the external environment on the vibrating string sensor, some methods of temperature compensation for the vibrating string sensor are used to fuse the sensor output data, which greatly reduces the temperature error; some methods analyze the output signal spectrum of the sensor before pre-excitation, identify the noise source, and filter it out in the spectrum of the output signal after pre-excitation; some methods use the frequency domain method to measure the output frequency of the vibrating string sensor, which can effectively improve the measurement accuracy, and at the same time obtain the signal-to-noise ratio and signal attenuation rate. At present, domestic and foreign scholars have achieved many results on how to reduce the impact of external interference on the measurement of vibrating string sensors, but there is less research on the failure and repair of vibrating string sensors. Often, the vibrating string sensor is installed and buried with the main project during the construction period, and most of them have been put into use for many years. Many vibrating string sensors have problems such as poor burial and insufficient excitation, resulting in the sensor not working or poor working effect. These problems are sometimes far more serious than the interference caused by the harsh external environment. Summary of the invention

[0004] Purpose of the invention: The purpose of the present invention is to provide a method, system, device and storage medium for vibrating string sensor fault diagnosis and repair, which can accurately and effectively perform fault diagnosis and online real-time monitoring of vibrating string sensors, and quickly repair vibrating string sensors with faults.

[0005] Technical solution: A method for diagnosing and repairing a vibrating string sensor fault of the present invention comprises:

[0006] Exciting and picking up vibrations on a vibrating string sensor, and collecting an output signal of the vibrating string sensor, wherein the vibrating string sensor includes a vibrating string sensor that is working normally and a vibrating string sensor that is faulty, and the output signal includes an amplitude and a frequency;

[0007] Amplify the amplitude of all the collected vibrating wire sensor output signals and filter them using a bandpass filter circuit so that the output frequency remains within a preset range;

[0008] A basic fault diagnosis and identification model is constructed, and the amplified and filtered data is input into the basic fault diagnosis and identification model, and the basic fault diagnosis and identification model is trained to obtain a fault diagnosis and identification model; the real-time collected vibrating string sensor output signal is amplified and filtered and then input into the fault diagnosis and identification model to perform feature extraction and classification, thereby identifying the vibrating string sensor with fault and its fault type;

[0009] Select different methods to repair the faulty vibrating wire sensor according to the fault type;

[0010] Display the diagnosis results and working status of the fault diagnosis and identification model and the real frequency of the repaired vibrating wire sensor;

[0011] All the above data are stored for subsequent analysis and iterative update of fault diagnosis and identification models.

[0012] Furthermore, the basic fault diagnosis and identification model is constructed, and the amplified and filtered data is input into the basic fault diagnosis and identification model, and the basic fault diagnosis and identification model is trained to obtain the fault diagnosis and identification model, including:

[0013] The amplified and filtered data is input into a one-dimensional convolutional neural network, and the important features of the input samples are automatically extracted through the convolution layer and the pooling layer. The faults are then classified through the classification layer to construct a basic fault diagnosis and identification model. The basic fault diagnosis and identification model is then trained and its performance is evaluated to obtain a fault diagnosis and identification model.

[0014] Furthermore, the fault types include that the steel string or base of the vibrating string sensor is completely loose, the wiring of the vibrating string sensor is too long or the excitation is poor, and the vibrating string sensor works normally but the buried area is poor, resulting in large interference noise of the vibrating string sensor.

[0015] Furthermore, different methods are selected according to the fault type to repair the faulty vibrating wire sensor, including:

[0016] When repairing a vibrating-wire sensor with too long wiring or poor excitation, the output amplitude and frequency of the vibrating-wire sensor are measured using short-time Fourier transform, and the output frequency of the faulty vibrating-wire sensor attenuated by the noise is extracted;

[0017] After amplifying the extracted attenuated signal amplitude, the amplitude is fitted with the output signal amplitude of the vibrating string sensor in normal operation to verify whether it meets the normal operation signal amplitude attenuation law;

[0018] If the normal working signal amplitude attenuation law is met, the attenuated signal frequency is used as the output frequency of the vibrating string sensor to complete the repair; if it is not met, the next working cycle is taken to repeat the verification.

[0019] Furthermore, the amplitude of all the collected vibrating-wire sensor output signals is amplified and filtered using a bandpass filter circuit so that the output frequency is maintained at 400-6000 Hz.

[0020] Furthermore, if the fault type is that the steel string or base of the vibrating wire sensor is completely loose, an alarm is activated.

[0021] Furthermore, if the fault type is that the vibrating string sensor works normally but the buried area is bad, resulting in large interference noise of the vibrating string sensor, the frequency domain measurement method is used to repair the fault.

[0022] Based on the same inventive concept, a vibrating wire sensor fault diagnosis and repair system of the present invention comprises:

[0023] A data acquisition module, used for exciting and picking up the vibrating string sensor, and collecting the output signal of the vibrating string sensor, wherein the vibrating string sensor includes a vibrating string sensor in normal operation and a vibrating string sensor with a fault, and the output signal includes an amplitude and a frequency;

[0024] A data preprocessing module is used to amplify the amplitude of all the collected vibrating-wire sensor output signals and filter them using a bandpass filter circuit so that the output frequency remains within a preset range;

[0025] The fault diagnosis and identification module is used to construct a basic fault diagnosis and identification model, and input the amplified and filtered data into the basic fault diagnosis and identification model, train the basic fault diagnosis and identification model, and obtain the fault diagnosis and identification model; amplify and filter the real-time collected vibrating string sensor output signal and input it into the fault diagnosis and identification model, perform feature extraction and classification, and thus identify the vibrating string sensor with fault and its fault type;

[0026] A fault repair module, used for selecting different methods to repair the faulty vibrating string sensor according to the fault type;

[0027] A user interface module, used to display the diagnosis result and working status of the fault diagnosis and identification model and the real frequency of the repaired vibrating string sensor;

[0028] The data storage module is used to store all the above data for subsequent analysis and iterative update of the fault diagnosis and identification model.

[0029] Based on the same inventive concept, a vibrating string sensor fault diagnosis and repair device of the present invention includes a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the above-mentioned vibrating string sensor fault diagnosis and repair method.

[0030] Based on the same inventive concept, a computer-readable storage medium of the present invention stores a computer program thereon, and when the program is executed by a processor, the steps of the above-mentioned vibrating string sensor fault diagnosis and repair method are implemented.

[0031] Beneficial effects: Compared with the prior art, the significant technical effects of the present invention are:

[0032] The present invention only needs to perform simple amplification and filtering on the vibrating string sensor to input the fault diagnosis and identification model for fault diagnosis, so it can realize online real-time status monitoring of the vibrating string sensor;

[0033] According to the characteristic that the output signal of the vibrating string sensor is constantly attenuated, the system can still accurately find the output frequency of the sensor under the harsh condition of low signal-to-noise ratio, thereby greatly reducing noise interference.

[0034] The present invention adopts a one-dimensional convolutional neural network with a diagnostic accuracy greater than 98%. At the same time, the repair method adopts short-time Fourier transform with high measurement accuracy and an error within 0.1 Hz, which can meet the measurement requirements of the vibrating string sensor and realize the repair of the vibrating string sensor in a fault condition, and has certain economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a flow chart of a method for diagnosing and repairing a vibrating string sensor fault disclosed in an embodiment of the present invention;

[0036] Figure 2 It is a flowchart of a fault diagnosis and identification and fault repair phase disclosed in an embodiment of the present invention;

[0037] Figure 3 It is a structural schematic diagram of a vibrating wire sensor fault diagnosis and repair system disclosed in an embodiment of the present invention;

[0038] Figure 4 It is a structural schematic diagram of a vibrating string sensor fault diagnosis and repair device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It will be understood by those skilled in the art that the purposes and advantages that can be achieved with the present invention are not limited to the specific description of the above beneficial effects, and the above and other purposes that can be achieved by the present invention will be more clearly understood based on the following detailed description.

[0040] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed in the present invention can be implemented in hardware, software or a combination of the two. Whether it is implemented in hardware or software depends on the specific application and design of the technical solution. Professional and technical personnel can use different methods to implement the functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0041] Reference to "embodiments" in the present invention means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0042] Example 1

[0043] See also Figure 1 , Figure 1 1 is a flow chart of a method for diagnosing and repairing a vibrating wire sensor fault disclosed in an embodiment of the present invention. Figure 1 The described vibrating string sensor fault diagnosis and repair method is applied to pumped storage power stations, such as being used for online real-time monitoring and fault diagnosis of vibrating string sensors in pumped storage power stations, and the embodiments of the present invention are not limited thereto. Figure 1 As shown, the vibrating wire sensor fault diagnosis and repair method may include the following operations:

[0044] S1. Excite and pick up the vibrating string sensor to collect the output signal of the vibrating string sensor, wherein the vibrating string sensor includes a vibrating string sensor in normal operation and a vibrating string sensor with a fault, and the output signal includes an amplitude and a frequency.

[0045] Collect enough samples of the vibrating wire sensor, including the signal amplitude of the normal working and faulty sensors.

[0046] S2. Amplify the amplitude of all the collected vibrating-wire sensor output signals, and filter them using a bandpass filter circuit so that the output frequency remains within a preset range.

[0047] In this embodiment, the amplitudes of all the collected vibrating-wire sensor output signals are amplified and filtered using a bandpass filter circuit so that the output frequency is maintained at 400-6000 Hz.

[0048] S3, such as Figure 2As shown, a basic fault diagnosis and identification model is constructed, and the amplified and filtered data is input into the basic fault diagnosis and identification model, and the basic fault diagnosis and identification model is trained to obtain the fault diagnosis and identification model; the real-time collected vibrating string sensor output signal is amplified and filtered and then input into the fault diagnosis and identification model for feature extraction and classification, so as to identify the vibrating string sensor with fault and its fault type.

[0049] Among them, a basic fault diagnosis and identification model is constructed, and the amplified and filtered data is input into the basic fault diagnosis and identification model, and the basic fault diagnosis and identification model is trained to obtain a fault diagnosis and identification model, including:

[0050] The amplified and filtered data is input into a one-dimensional convolutional neural network, and the important features of the input samples are automatically extracted through the convolution layer and the pooling layer. The faults are then classified through the classification layer to construct a basic fault diagnosis and identification model. The basic fault diagnosis and identification model is then trained and its performance is evaluated to obtain a fault diagnosis and identification model.

[0051] These samples are directly input into a one-dimensional convolutional neural network, and the important features of the input samples are automatically learned through convolution and pooling. Fault diagnosis and identification are then performed through the classification layer to construct a fault diagnosis and identification model for the vibrating string sensor.

[0052] Among them, the fault types include the steel string or base of the vibrating string sensor being completely loose, the wiring of the vibrating string sensor being too long or the excitation being poor, and the normal operation of the vibrating string sensor but the poor buried area resulting in large interference noise from the vibrating string sensor.

[0053] After a simple amplification and filtering process, the output signal amplitude of the vibrating string sensor is directly input into a one-dimensional convolutional neural network, which can realize online real-time fault diagnosis.

[0054] Compared with the method of manually extracting features and then performing fault diagnosis, the method of using one-dimensional convolutional neural network for fault diagnosis has a higher accuracy rate, which can reach more than 98%.

[0055] S4, such as Figure 2 As shown, different methods are selected according to the fault type to repair the faulty vibrating wire sensor;

[0056] In this embodiment, for the vibrating wire sensor whose fault type is too long wiring or poor excitation, the specific repair method is as follows:

[0057] When repairing a vibrating-wire sensor with too long wiring or poor excitation, the output amplitude and frequency of the vibrating-wire sensor are measured using short-time Fourier transform, and the output frequency of the faulty vibrating-wire sensor attenuated by the noise is extracted;

[0058] After amplifying the extracted attenuated signal amplitude, the amplitude is fitted with the output signal amplitude of the vibrating string sensor in normal operation to verify whether it meets the normal operation signal amplitude attenuation law;

[0059] If the normal working signal amplitude attenuation law is met, the attenuated signal frequency is used as the output frequency of the vibrating string sensor to complete the repair; if it is not met, the next working cycle is taken to repeat the verification.

[0060] The extracted attenuation signal is amplified and then fitted with the attenuation law of the output signal of the vibrating string sensor that works normally, to verify whether the attenuation signal is the output signal of the faulty sensor.

[0061] In this embodiment, if the fault type is that the steel string or base of the vibrating wire sensor is completely loose, an alarm is activated.

[0062] If the fault type is that the vibrating string sensor works normally but the buried area is bad, resulting in large interference noise of the vibrating string sensor, the frequency domain measurement method is used to repair the fault.

[0063] Short-time Fourier transform is used to obtain the output amplitude and frequency of the vibrating-wire sensor with too long wiring or poor excitation. The frequency measurement accuracy is high and can reach within 0.1Hz error, which meets the actual measurement requirements.

[0064] The output amplitude of the faulty vibrating-string sensor obtained by short-time Fourier transform is amplified and then fitted with the output amplitude of the normally working vibrating-string sensor to further verify that the attenuated signal is the working signal of the vibrating-string sensor.

[0065] The continuous attenuation of the output signal of the vibrating-wire sensor is adopted as the signal feature, which can effectively reduce the interference of noise.

[0066] By using short-time Fourier transform, under the harsh condition of low signal-to-noise ratio, the vibrating-wire sensor with too long wiring or poor excitation can be repaired by finding the attenuated vibrating-wire sensor output signal.

[0067] S5, displaying the diagnosis result and working status of the fault diagnosis and identification model and the real frequency of the repaired vibrating string sensor;

[0068] The operator can easily view the diagnostic results and working status of the vibrating wire sensor diagnostic model. At the same time, the real frequency of the vibrating wire sensor after repairing the vibrating wire sensor with too long wiring or poor excitation can be obtained to measure the stress.

[0069] S6. Store all the above data for subsequent analysis and iterative update of the fault diagnosis and identification model.

[0070] Store training data, test data, diagnosis results, repair results, etc. to facilitate subsequent analysis and model iteration, thereby improving the accuracy of model recognition.

[0071] The technical solution of the present invention is to input the output signal amplitude of the vibrating wire sensor based on three common fault causes together with the output signal amplitude of the normal sensor into a one-dimensional convolutional neural network for fault diagnosis and identification classification. Short-time Fourier transform is used to repair faulty sensors with too long wiring or insufficient excitation voltage.

[0072] Example 2

[0073] See also Figure 3 , Figure 3 1 is a schematic diagram of a structure of a vibrating string sensor fault diagnosis and repair system disclosed in an embodiment of the present invention. The system can realize online real-time monitoring and fault diagnosis of the vibrating string sensor, and specifically includes:

[0074] A data acquisition module, used for exciting and picking up the vibrating string sensor, and collecting the output signal of the vibrating string sensor, wherein the vibrating string sensor includes a vibrating string sensor in normal operation and a vibrating string sensor with a fault, and the output signal includes an amplitude and a frequency;

[0075] A data preprocessing module is used to amplify the amplitude of all the collected vibrating-wire sensor output signals and filter them using a bandpass filter circuit so that the output frequency remains within a preset range;

[0076] The fault diagnosis and identification module is used to construct a basic fault diagnosis and identification model, and input the amplified and filtered data into the basic fault diagnosis and identification model, train the basic fault diagnosis and identification model, and obtain the fault diagnosis and identification model; amplify and filter the real-time collected vibrating string sensor output signal and input it into the fault diagnosis and identification model, perform feature extraction and classification, and thus identify the vibrating string sensor with fault and its fault type;

[0077] A fault repair module, used for selecting different methods to repair the faulty vibrating string sensor according to the fault type;

[0078] A user interface module, used to display the diagnosis result and working status of the fault diagnosis and identification model and the real frequency of the repaired vibrating string sensor;

[0079] The data storage module is used to store all the above data for subsequent analysis and iterative update of the fault diagnosis and identification model.

[0080] In an optional embodiment, a method for diagnosing and repairing a vibrating string sensor fault includes: a) exciting and picking up the vibrating string sensor to collect the output signal of the vibrating string sensor; b) amplifying the amplitude of all collected vibrating string sensor output signals, and filtering them using a bandpass filter circuit so that the output frequency remains within a preset range; c) inputting the amplified and filtered data into a pre-built fault diagnosis and identification model to perform feature extraction and classification, thereby identifying the vibrating string sensor with a fault and its fault type; d) selecting different methods to repair the vibrating string sensor with a fault according to the fault type; e) displaying the diagnosis result and working status of the fault diagnosis and identification model and the true frequency of the repaired vibrating string sensor; and f) storing all the above data.

[0081] In one embodiment, the fault diagnosis and identification module includes a CNN feature extraction module and a model training and evaluation module. The CNN feature extraction module is used to input the amplified filtered data into a one-dimensional convolutional neural network, automatically extract important features of the input samples through convolution layers, pooling layers, etc., and then perform fault classification through the classification layer to construct an initial fault diagnosis and identification model, and use the model training and evaluation module to train and evaluate the performance of the initial fault diagnosis and identification model.

[0082] The fault diagnosis and identification module trains the input samples through a convolutional neural network and constructs a vibrating string sensor diagnostic model. The diagnostic identification accuracy is high and online real-time monitoring can be achieved.

[0083] In one embodiment, the fault repair module includes an attenuated signal extraction module and an attenuated signal verification module. The attenuated signal extraction module extracts the vibrating string sensor working signal that is submerged by noise and is attenuating. The attenuated signal verification module amplifies the extracted attenuated signal and fits it with the attenuation law of the vibrating string sensor that is working normally, thereby verifying whether it is the output signal of the faulty vibrating string sensor.

[0084] The fault repair module uses short-time Fourier transform to extract the output frequency of the faulty vibrating-wire sensor that is attenuated by the noise.

[0085] The fault repair module needs to collect the attenuated working signal, so the short-time Fourier transform is an effective method to obtain the frequency component of the time-varying signal.

[0086] In one embodiment, the user interface module can monitor the working state of the vibrating-wire sensor in real time, which is helpful to find the cause of the failure of the vibrating-wire sensor. The user interface module provides a friendly user interface, so that the operator can easily view the diagnosis results and working state of the vibrating-wire sensor diagnosis model. At the same time, the real frequency of the vibrating-wire sensor after repairing the vibrating-wire sensor with too long wiring or poor excitation can also be obtained, so as to measure the stress.

[0087] In one embodiment, the data storage module stores training data, test data, diagnosis results, repair results, etc. to facilitate subsequent analysis and model iteration, thereby improving the accuracy of system recognition.

[0088] Example 3

[0089] See also Figure 4 , Figure 4 1 is a schematic diagram of a vibrating wire sensor fault diagnosis and repair device disclosed in an embodiment of the present invention. Figure 4 The described device can be applied in a pumped storage power station, such as being used for online real-time monitoring and fault diagnosis of a vibrating wire sensor, and the embodiments of the present invention are not limited thereto.

[0090] like Figure 4 As shown, the device may include a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the method described in the above embodiment and can achieve the technical effect consistent with the above method.

[0091] The memory may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the memory may be used to read and write non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). A program / utility having a set (at least one) of program modules may be stored in, for example, the memory, such program modules including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include the implementation of a network environment. The program modules typically perform the functions and / or methods in the embodiments described herein.

[0092] The processor executes various functional applications and data processing by running the program stored in the memory, such as implementing the method provided in the first embodiment of the present invention.

[0093] Example 4

[0094] Embodiment 4 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method described in the above embodiment are implemented and the technical effect consistent with the above method can be achieved.

[0095] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0096] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0097] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0098] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or combinations thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0099] Of course, the storage medium containing computer executable instructions provided by an embodiment of the present invention, whose computer executable instructions are not limited to the above method operations, can also execute related operations in the method provided by any embodiment of the present invention.

[0100] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for diagnosing and repairing a vibrating wire sensor fault, characterized in that: include: Exciting and picking up vibrations on a vibrating string sensor, and collecting an output signal of the vibrating string sensor, wherein the vibrating string sensor includes a vibrating string sensor that is working normally and a vibrating string sensor that is faulty, and the output signal includes an amplitude and a frequency; Amplify the amplitude of all the collected vibrating wire sensor output signals and filter them using a bandpass filter circuit so that the output frequency remains within a preset range; A basic fault diagnosis and identification model is constructed, and the amplified and filtered data is input into the basic fault diagnosis and identification model, and the basic fault diagnosis and identification model is trained to obtain a fault diagnosis and identification model; the real-time collected vibrating string sensor output signal is amplified and filtered and then input into the fault diagnosis and identification model to perform feature extraction and classification, thereby identifying the vibrating string sensor with fault and its fault type; Select different methods to repair the faulty vibrating wire sensor according to the fault type; Display the diagnosis results and working status of the fault diagnosis and identification model and the real frequency of the repaired vibrating wire sensor; All the above data are stored for subsequent analysis and iterative update of fault diagnosis and identification models.

2. The method for diagnosing and repairing a vibrating wire sensor fault according to claim 1, characterized in that: Construct a basic fault diagnosis and identification model, input the amplified and filtered data into the basic fault diagnosis and identification model, train the basic fault diagnosis and identification model, and obtain a fault diagnosis and identification model, including: The amplified and filtered data is input into a one-dimensional convolutional neural network, and the important features of the input samples are automatically extracted through the convolution layer and the pooling layer. The faults are then classified through the classification layer to construct a basic fault diagnosis and identification model. The basic fault diagnosis and identification model is then trained and its performance is evaluated to obtain a fault diagnosis and identification model.

3. The method for diagnosing and repairing a vibrating wire sensor fault according to claim 1, characterized in that: The fault types include: the steel string or base of the vibrating string sensor is completely loose, the wiring of the vibrating string sensor is too long or the excitation is poor, and the vibrating string sensor works normally but the buried area is poor, resulting in large interference noise of the vibrating string sensor.

4. The method for diagnosing and repairing a vibrating wire sensor fault according to claim 3, characterized in that: Depending on the fault type, different methods are selected to repair the faulty vibrating wire sensor, including: When repairing a vibrating-wire sensor with too long wiring or poor excitation, the output amplitude and frequency of the vibrating-wire sensor are measured using short-time Fourier transform, and the output frequency of the faulty vibrating-wire sensor attenuated by the noise is extracted; After amplifying the extracted attenuated signal amplitude, the amplitude is fitted with the output signal amplitude of the vibrating string sensor in normal operation to verify whether it meets the normal operation signal amplitude attenuation law; If the normal working signal amplitude attenuation law is met, the attenuated signal frequency is used as the output frequency of the vibrating string sensor to complete the repair; if it is not met, the next working cycle is taken to repeat the verification.

5. The vibrating wire sensor fault diagnosis and repair method according to claim 1, characterized in that: The amplitude of all the collected vibrating-wire sensor output signals is amplified and filtered using a bandpass filter circuit so that the output frequency is maintained at 400-6000 Hz.

6. The method for diagnosing and repairing a vibrating wire sensor fault according to claim 3, characterized in that: If the fault type is that the vibrating wire sensor steel string or base is completely loose, the alarm will be activated.

7. The method for diagnosing and repairing a vibrating wire sensor fault according to claim 3, characterized in that: If the fault type is that the vibrating string sensor works normally but the buried area is bad, resulting in large interference noise of the vibrating string sensor, the frequency domain measurement method is used to repair the fault.

8. A vibrating wire sensor fault diagnosis and repair system, characterized in that: include: A data acquisition module, used for exciting and picking up the vibrating string sensor, and collecting the output signal of the vibrating string sensor, wherein the vibrating string sensor includes a vibrating string sensor in normal operation and a vibrating string sensor with a fault, and the output signal includes an amplitude and a frequency; A data preprocessing module is used to amplify the amplitude of all the collected vibrating-wire sensor output signals and filter them using a bandpass filter circuit so that the output frequency remains within a preset range; The fault diagnosis and identification module is used to construct a basic fault diagnosis and identification model, and input the amplified and filtered data into the basic fault diagnosis and identification model, train the basic fault diagnosis and identification model, and obtain the fault diagnosis and identification model; amplify and filter the real-time collected vibrating string sensor output signal and input it into the fault diagnosis and identification model, perform feature extraction and classification, and thus identify the vibrating string sensor with fault and its fault type; A fault repair module, used for selecting different methods to repair the faulty vibrating string sensor according to the fault type; A user interface module, used to display the diagnosis result and working status of the fault diagnosis and identification model and the real frequency of the repaired vibrating string sensor; The data storage module is used to store all the above data for subsequent analysis and iterative update of the fault diagnosis and identification model.

9. A vibrating wire sensor fault diagnosis and repair device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the vibrating string sensor fault diagnosis and repair method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the vibrating-wire sensor fault diagnosis and repair method according to any one of claims 1 to 7.

Images