CN115711669A - Method, device, terminal and storage medium for diagnosing faults of shaft equipment - Google Patents
Method, device, terminal and storage medium for diagnosing faults of shaft equipment Download PDFInfo
- Publication number
- CN115711669A CN115711669A CN202211384592.2A CN202211384592A CN115711669A CN 115711669 A CN115711669 A CN 115711669A CN 202211384592 A CN202211384592 A CN 202211384592A CN 115711669 A CN115711669 A CN 115711669A
- Authority
- CN
- China
- Prior art keywords
- audio
- model
- features
- abnormal
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The application provides a method, a device, a terminal and a storage medium for diagnosing faults of shaft equipment. The method comprises the following steps: collecting vibration audio data of the shaft equipment; extracting audio features from the vibration audio data based on a voiceprint recognition model, and judging feature types of the audio features, wherein the feature types comprise normal features and abnormal features, the voiceprint recognition model comprises a feature extraction model and an abnormal judgment model, the feature extraction model is obtained based on fusion of an LSTM neural network and a residual error network, and the abnormal judgment model is obtained based on Gaussian mixture model construction; and if the audio features are abnormal features, determining fault types corresponding to the audio features based on the fault judgment model. The method and the device can timely and accurately diagnose various abnormal states of the wellbore equipment which is distributed in a long distance and has a complex environment.
Description
Technical Field
The present disclosure relates to the field of fault diagnosis technologies, and in particular, to a method, an apparatus, a terminal, and a storage medium for diagnosing a fault of a wellbore device.
Background
The vertical shaft cage is one of the most important production devices in coal mines, is responsible for lifting coal and materials, transportation personnel and various devices, plays a great role in mine lifting, can be connected with the ground and underground, and the safe and stable operation of the cage and the head sheave is an important safety guarantee for the production personnel and materials.
At present, the point sensor is usually adopted to carry out fault interception on coal mine equipment so as to realize monitoring on safe and stable operation of the coal mine equipment, but the point sensor cannot solve long-distance distributed monitoring, cannot be installed in a complex environment and a passive environment, and cannot monitor the equipment state on line in real time.
Disclosure of Invention
The application provides a method, a device, a terminal and a storage medium for diagnosing faults of shaft equipment, which aim to solve the problem that the fault diagnosis of the shaft equipment cannot be carried out in real time under the conditions of long-distance distribution and complex environment in the prior art.
In a first aspect, the present application provides a method of diagnosing a failure of a wellbore device, comprising:
collecting vibration audio data of the shaft equipment;
extracting audio features from the vibration audio data based on a voiceprint recognition model, and judging feature types of the audio features, wherein the feature types comprise normal features and abnormal features, the voiceprint recognition model comprises a feature extraction model and an abnormal judgment model, the feature extraction model is obtained based on fusion of an LSTM neural network and a residual error network, and the abnormal judgment model is obtained based on construction of a Gaussian mixture model;
and if the audio features are abnormal features, determining the fault type corresponding to the audio features based on a fault judgment model.
In a second aspect, the present application provides a wellbore equipment failure diagnosis apparatus, comprising:
the acquisition module is used for acquiring vibration audio data of the shaft equipment;
the recognition module is used for extracting audio features from the vibration audio data based on a voiceprint recognition model and judging the feature types of the audio features, wherein the feature types comprise normal features and abnormal features, the voiceprint recognition model comprises a feature extraction model and an abnormal judgment model, the feature extraction model is obtained based on fusion of an LSTM neural network and a residual error network, and the abnormal judgment model is obtained based on construction of a Gaussian mixture model;
and the determining module is used for determining the fault type corresponding to the audio feature based on a fault judgment model if the audio feature is an abnormal feature.
In a third aspect, the present application provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method for diagnosing the failure of the wellbore equipment as described in the first aspect or any one of the possible implementations of the first aspect.
In a fourth aspect, the present application provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method for diagnosing a failure of a wellbore device as described above in the first aspect or any one of the possible implementations of the first aspect.
The application provides a method, a device, a terminal and a storage medium for diagnosing faults of shaft equipment, wherein vibration audio data of the shaft equipment are acquired, and due to the installation environment of the shaft equipment, the vibration data acquisition of the shaft equipment which is distributed in a long distance and has a complex environment can be realized; extracting audio features from the vibration audio data based on a voiceprint recognition model, and judging feature types of the audio features, wherein the feature types comprise normal features and abnormal features, the voiceprint recognition model comprises a feature extraction model and an abnormal judgment model, the feature extraction model is obtained based on fusion of an LSTM neural network and a residual error network, and the abnormal judgment model is obtained based on Gaussian mixture model construction; if the audio features are abnormal features, the fault type corresponding to the audio features is determined based on the fault determination model, various abnormal states of the wellbore equipment which is distributed in a long distance and has a complex environment can be diagnosed timely and accurately, further serious faults are prevented according to the diagnosis result, the running safety, reliability and effectiveness of the wellbore equipment are improved, the fault loss is reduced to the minimum, and the equipment is ensured to exert the maximum economic benefit.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the embodiments or the prior art description will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings may be obtained according to these drawings without inventive labor.
FIG. 1 is a flow chart of an implementation of a method for diagnosing a failure of a wellbore device provided by an embodiment of the present application;
fig. 2 is a routing diagram of a distributed optical fiber according to an embodiment of the present application;
FIG. 3 is an audio schematic of a normal feature provided by an embodiment of the present application;
FIG. 4 is an audio frequency schematic view of bolt loosening provided by an embodiment of the present application;
FIG. 5 is an audio schematic diagram of a collision of a cage with a rail provided by an embodiment of the present application;
FIG. 6 is a schematic structural diagram of a wellbore equipment failure diagnosis device provided by an embodiment of the application;
fig. 7 is a schematic diagram of a terminal according to an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
To make the objects, technical solutions and advantages of the present application more apparent, the following description is given by way of example with reference to the accompanying drawings.
Fig. 1 is a flowchart of an implementation of a method for diagnosing a failure of a wellbore device according to an embodiment of the present application, which is detailed as follows:
in S101, vibration audio data of the wellbore device is acquired.
There are many factors due to the unsafe nature of the wellbore equipment, such as: the equipment is not regularly checked and maintained, so that the strain of some equipment is not timely discovered, the steel wire rope is pulled off, the brake valve fails, the derrick inclines, the indicator and the falling protector fail, the abrasion and corrosion are serious, even the safety coefficient does not reach the standard, and the equipment with unqualified quality inspection is always used.
Moreover, the shaft can produce different sounds under different mechanical conditions, the sounds all have unique characteristics, the cage shaft is the main hoisting passage of the mine, in the hoisting process, the machine running friction produces different characteristic sounds, because of the physical attributes of the voice: tone quality, duration, intensity and pitch, physical characteristic quantity are different, thus the voice presents different voiceprint characteristics on the voiceprint atlas, therefore, the rules of normal operation and abnormal operation of the machine equipment can be found out according to the voiceprint characteristic parameters.
Therefore, this application is gathered the vibration audio data of pit shaft equipment, carries out the analysis to the vibration audio data who gathers, judges whether pit shaft equipment is safe.
In one possible implementation, acquiring vibration audio data of a wellbore device may include:
vibration audio data of the wellbore device is collected through the distributed optical fiber.
Referring to fig. 2, it can be seen that the distributed optical fiber is laid along equipment such as a lifting container track and a head sheave, and vibration audio data in real-time operation of the equipment such as the lifting container and the head sheave are obtained in time, wherein the shaft equipment comprises the lifting container, the head sheave and the like.
Distributed optical fibers, i.e., distributed optical fiber sensors, are sensors that employ unique distributed optical fiber detection techniques to measure or monitor spatially distributed and time varying information along an optical fiber transmission path.
By adopting the distributed optical fiber, the vibration audio data in real-time operation of equipment such as a lifting container, a head sheave and the like can be acquired under the installation of a long-distance distribution complex environment and a passive environment, and the effectiveness of data acquisition is improved.
In one possible implementation, the vibration audio data may further include position data for lifting the container, and the method may further include:
and outputting alarm information of the vibration audio data, wherein the alarm information comprises an alarm type and corresponding position data.
In the embodiment of the application, the distributed optical fiber is laid along equipment such as the lifting container track and the head sheave, so that the vibration audio frequency of the lifting container in real-time operation can be timely acquired, and the distributed optical fiber is deployed in a shaft track gap to monitor the position of the lifting container in real time by matching with a positioning system or positioning equipment.
According to the obtained vibration audio data of the lifting container and the position data of the lifting container, if the vibration audio data of the current lifting container is abnormal, alarm information of the vibration audio data can be output, wherein the alarm information can comprise alarm types and position data of the lifting container with the abnormality, for example, referring to fig. 2, if the vibration audio data of the lifting container at the position A in the main shaft has screw loosening abnormality, the output alarm information is bolt loosening abnormality and the position A of the lifting container in the main shaft.
In S102, based on a voiceprint recognition model, extracting audio features from the vibration audio data, and judging feature types of the audio features, wherein the feature types include normal features and abnormal features, the voiceprint recognition model includes a feature extraction model and an abnormal judgment model, the feature extraction model is obtained based on fusion of an LSTM neural network and a residual error network, and the abnormal judgment model is obtained based on construction of a Gaussian mixture model.
In the embodiment of the application, the voiceprint recognition model comprises a feature extraction model and an abnormality determination model, wherein the feature extraction model is obtained based on fusion of an LSTM neural network and a residual error network, the abnormality determination model is obtained based on Gaussian mixture model construction, the voiceprint recognition model is used for extracting the audio features of the shaft equipment, including the feature attributes such as friction, vibration, power and quality, and the feature types of the shaft equipment are predicted through historical attribute state change comparison and attribute quantization type comparison.
The LSTM (Long Short-Term Memory network) is a time-cycle neural network, and is specially designed to solve the Long-Term dependence problem of general RNNs (cyclic neural networks), and all RNNs have a chain form of a repetitive neural network module.
The principle of the residual error network is obtained by transforming the convolutional neural network. The convolution block of each layer of convolution neural network is generally 3 x 3 in shape, the characteristics of the signal are extracted through translation, the final output signal is a vector of 256 x 1, and the vector is judged to be normal or abnormal through a clustering algorithm.
In the embodiment of the application, the LSTM neural network and the residual error network are fused to obtain a feature extraction model, and the feature extraction model is mainly used for extracting the audio features corresponding to the time sequence audio signals.
A Gaussian Mixed Model (GMM) accurately quantifies objects using a Gaussian probability density function (normal distribution curve), and is a Model that decomposes objects into a plurality of objects based on the Gaussian probability density function (normal distribution curve).
The abnormity judgment model constructed based on the Gaussian mixture model in the embodiment of the application is mainly used for judging the characteristic types of the audio characteristics extracted by the characteristic extraction model, wherein the characteristic types comprise normal characteristics and abnormal characteristics.
In one possible implementation, S102 may include:
calculating the vibration audio data by adopting a Mel frequency cepstrum coefficient to obtain a time sequence audio signal;
and extracting audio features from the time-series audio signal based on the feature extraction model, and judging the feature type of the audio features based on the abnormity judgment model.
In the embodiment of the application, before feature extraction and feature type judgment, the acquired vibration audio data of the wellbore equipment needs to be subjected to mel-frequency cepstrum coefficient calculation to obtain a time sequence audio signal corresponding to the vibration audio data.
Here, mel-Frequency Cepstral Coefficients (MFCCs) are Coefficients constituting Mel-Frequency cepstrum. In the field of sound processing, mel-Frequency Cepstrum (Mel-Frequency Cepstrum) is a linear transformation of the log energy spectrum based on the nonlinear Mel scale (Mel scale) of sound frequencies.
Calculating a Mel frequency cepstrum coefficient to obtain a time series audio signal, inputting the time series audio signal into a feature extraction model to obtain audio features corresponding to the time series audio signal, wherein the audio features are one-dimensional vectors; and inputting the audio feature vector into an abnormality judgment model to obtain a feature type corresponding to the audio feature.
In one possible implementation, the training process of the voiceprint recognition model may include:
carrying out fusion connection on the LSTM neural network and the residual error network;
taking the time series audio signal as input, taking the audio characteristic corresponding to the time series audio signal as output, and training the LSTM neural network and the residual error network after fusion connection to obtain a characteristic extraction model;
and training an abnormality judgment model constructed based on a Gaussian mixture model by taking the audio feature vector as input and the feature type corresponding to the audio feature as output to obtain the abnormality judgment model.
The training process of the voiceprint recognition model in the embodiment of the application can comprise the following steps:
firstly, training a feature extraction model, taking a time sequence audio signal as input, taking audio features corresponding to the time sequence audio signal as output, and training the feature extraction model obtained based on the fusion of an LSTM neural network and a residual error network to obtain the trained feature extraction model, wherein the audio features output by the feature extraction model are one-dimensional vectors;
and then, training the abnormal judgment model constructed based on the GMM by taking the audio feature vector output by the feature extraction model as input and the feature type corresponding to the audio feature as output to obtain the trained abnormal judgment model.
In which the sequence lengths of input and output for different types of time-series audio signals in the LSTM neural network are identical, which may cause variations in amplitude, spectrum, and vocal print when an abnormality occurs.
The output of the abnormality judgment model is a feature type, or a score value, wherein the score value is a weighted logarithmic probability value, and the feature type is judged according to the score value.
In one possible implementation manner, after S102, the method may further include:
clustering the audio features and historical audio features of the shaft equipment, and judging whether the distance between the audio features and a clustering center is greater than a preset deviation;
if the distance between the audio features and the clustering center is larger than the preset deviation, an early warning prompt is sent out through the distributed optical fiber connection optical fiber monitoring early warning host, and the early warning prompt is used for analyzing dangerous factors existing in the shaft equipment and reminding a user of maintaining the shaft equipment in time.
And storing the audio features corresponding to the time series audio signals obtained according to the feature extraction model, clustering the audio features with the historical audio features of the shaft equipment, calculating the distance d between the audio features and a clustering center, and judging the size relation between the distance d and a preset deviation epsilon.
If d is less than or equal to epsilon, the historical operating conditions of the shaft equipment corresponding to the current time series audio signal and the shaft equipment are not different, the shaft equipment is in a safe operating state, and maintenance is not needed.
If d is larger than epsilon, it is indicated that the operation state of the shaft equipment corresponding to the current time series audio signal has larger deviation with the historical operation state of the shaft equipment, and an early warning prompt is sent out through an optical fiber monitoring early warning host connected with the distributed optical fiber to analyze the dangerous factors existing in the shaft equipment and remind a user of maintaining the shaft equipment in time.
In S103, if the audio feature is an abnormal feature, the fault type corresponding to the audio feature is determined based on the fault determination model.
And judging and determining that the extracted audio features are abnormal features according to the S102, inputting the abnormal features as input into a fault judgment model, and determining the fault type corresponding to the audio features.
In one possible implementation, the fault determination model training process may include:
acquiring abnormal characteristics of fault audio of a determined fault type, taking the abnormal characteristics as a training sample, and taking a fault type corresponding to the abnormal characteristics as a label of the training sample, wherein the fault type comprises screw looseness and track abnormity;
and training the VGG network by adopting the training samples to obtain a fault judgment model.
In the embodiment of the application, a VGG network is used as a fault determination model, abnormal features of fault audio of a determined fault type are collected, the abnormal features are used as training samples, the fault type corresponding to the abnormal features is used as a label of the training samples, and the VGG network is trained to obtain the trained fault determination model.
In the embodiment of the application, the fault determination model comprises a plurality of fault types, for example, a fault type of abnormal sound caused by cracks, bolt looseness and displacement of wellbore equipment, or when the equipment is abnormal, when a cage runs on a rail, collision or periodic sound is generated, and the voiceprint of the sound changes, but for an unusual fault type, the class library of the model needs to be periodically and gradually expanded, and the recognition effect of the fault determination model is optimized.
A method for diagnosing a failure of a wellbore device is illustrated by one embodiment.
Referring to fig. 2, first, vibration audio data of a wellbore device is collected.
And secondly, calculating by adopting a Mel frequency cepstrum coefficient to obtain a time sequence audio signal corresponding to the vibration audio data.
Thirdly, extracting corresponding audio features from the time-series audio signals by using a feature extraction model in the voiceprint recognition model, judging the feature types corresponding to the audio features by using an abnormality judgment model according to the audio features, wherein if the feature types are normal features, the fault type judgment is not needed, and the audio schematic diagram refers to fig. 3 at the moment, so that the sound is gentle; and if the characteristic type is the abnormal characteristic, judging the fault type.
Fourthly, determining the fault type corresponding to the audio frequency characteristic according to the fault determination model, for example, if the fault type is bolt loosening, the audio frequency diagram at the moment refers to fig. 4, wherein the upper half part of fig. 4 is a timing diagram, when the bolt loosening occurs, a clicking sound occurs, the amplitude becomes large, and a frequency change from high to low is generated on the frequency; if the failure type is a collision between the cage and the rail, the audio frequency diagram in this case refers to fig. 5, which generates a wide audio frequency.
As is apparent from the audio frequency diagrams of fig. 3, 4 and 5, the audio frequency fluctuation when the equipment is abnormal is large, and according to the embodiment of the application, various abnormal states of the wellbore equipment can be diagnosed timely and accurately.
The application provides a shaft equipment fault diagnosis method, which can realize the vibration data acquisition of shaft equipment which is distributed in a long distance and has a complex environment by acquiring the vibration audio data of the shaft equipment and the installation environment of the shaft equipment; extracting audio features from the vibration audio data based on a voiceprint recognition model, and judging feature types of the audio features, wherein the feature types comprise normal features and abnormal features, the voiceprint recognition model comprises a feature extraction model and an abnormal judgment model, the feature extraction model is obtained based on fusion of an LSTM neural network and a residual error network, and the abnormal judgment model is obtained based on Gaussian mixture model construction; if the audio features are abnormal features, the fault type corresponding to the audio features is determined based on the fault determination model, various abnormal states of the wellbore equipment which is distributed in a long distance and has a complex environment can be diagnosed timely and accurately, further serious faults are prevented according to the diagnosis result, the running safety, reliability and effectiveness of the wellbore equipment are improved, the fault loss is reduced to the minimum, and the equipment is ensured to exert the maximum economic benefit.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
The following are apparatus embodiments of the present application, and for details not described in detail therein, reference may be made to the corresponding method embodiments described above.
Fig. 6 shows a schematic structural diagram of a wellbore equipment fault diagnosis device provided in an embodiment of the present application, and for convenience of explanation, only the parts related to the embodiment of the present application are shown, which are detailed as follows:
as shown in fig. 6, the well equipment failure diagnosis device 6 includes:
the acquisition module 61 is used for acquiring vibration audio data of the shaft equipment;
the recognition module 62 is configured to extract audio features from the vibration audio data based on a voiceprint recognition model, and determine feature types of the audio features, where the feature types include normal features and abnormal features, the voiceprint recognition model includes a feature extraction model and an abnormal determination model, the feature extraction model is obtained based on fusion of an LSTM neural network and a residual error network, and the abnormal determination model is obtained based on construction of a gaussian mixture model;
and the determining module 63 is configured to determine a fault type corresponding to the audio feature based on the fault determination model if the audio feature is an abnormal feature.
The application provides a shaft equipment fault diagnosis device, which can realize the vibration data acquisition of shaft equipment which is distributed in a long distance and has a complex environment by acquiring the vibration audio data of the shaft equipment and the installation environment of the shaft equipment; extracting audio features from the vibration audio data based on a voiceprint recognition model, and judging feature types of the audio features, wherein the feature types comprise normal features and abnormal features, the voiceprint recognition model comprises a feature extraction model and an abnormal judgment model, the feature extraction model is obtained based on fusion of an LSTM neural network and a residual error network, and the abnormal judgment model is obtained based on Gaussian mixture model construction; if the audio features are abnormal features, the fault types corresponding to the audio features are determined based on the fault determination model, various abnormal states of the wellbore equipment which is distributed in a long distance and has a complex environment can be diagnosed timely and accurately, further serious faults are prevented according to the diagnosis result, the safety, the reliability and the effectiveness of the operation of the wellbore equipment are improved, the fault loss is reduced to the minimum, and the equipment is ensured to exert the maximum economic benefit.
In a possible implementation manner, the acquisition module may be specifically configured to:
vibration audio data of the wellbore equipment is collected through the distributed optical fiber.
In a possible implementation manner, the vibration audio data may further include position data of the lifting container, and the apparatus may further include an alarm module, where the alarm module is configured to:
and outputting alarm information of the vibration audio data, wherein the alarm information comprises an alarm type and corresponding position data.
In one possible implementation, the identification module may be configured to:
calculating the vibration audio data by adopting a Mel frequency cepstrum coefficient to obtain a time sequence audio signal;
and extracting audio features from the time-series audio signal based on the feature extraction model, and judging the feature type of the audio features based on the abnormity judgment model.
In one possible implementation, the training process of the voiceprint recognition model may include:
carrying out fusion connection on the LSTM neural network and the residual error network;
taking the time sequence audio signal as input, taking the audio feature corresponding to the time sequence audio signal as output, and training the LSTM neural network and the residual error network after fusion connection to obtain a feature extraction model;
and training an abnormity judgment model constructed based on a Gaussian mixture model by taking the audio characteristic vector as input and the characteristic type corresponding to the audio characteristic as output to obtain the abnormity judgment model.
In one possible implementation, the fault determination model training process may include:
acquiring abnormal characteristics of fault audio of a determined fault type, taking the abnormal characteristics as a training sample, and taking a fault type corresponding to the abnormal characteristics as a label of the training sample, wherein the fault type comprises screw looseness and track abnormity;
and training the VGG network by adopting the training samples to obtain a fault judgment model.
In a possible implementation manner, after the identification module, the apparatus may further include an early warning module, where the early warning module is configured to:
clustering the audio features and historical audio features of the shaft equipment, and judging whether the distance between the audio features and a clustering center is greater than a preset deviation;
if the distance between the audio features and the clustering center is larger than the preset deviation, an early warning prompt is sent out through the distributed optical fiber connection optical fiber monitoring early warning host, and the early warning prompt is used for analyzing dangerous factors existing in the shaft equipment and reminding a user of maintaining the shaft equipment in time.
Fig. 7 is a schematic diagram of a terminal according to an embodiment of the present application. As shown in fig. 7, the terminal 7 of this embodiment includes: a processor 70, a memory 71 and a computer program 72 stored in said memory 71 and executable on said processor 70. The processor 70, when executing the computer program 72, implements the steps in the various wellbore equipment failure diagnosis method embodiments described above, such as S01-S103 shown in fig. 1. Alternatively, the processor 70, when executing the computer program 72, implements the functions of each module/unit in each device embodiment described above, for example, the functions of the modules 61 to 63 shown in fig. 6.
Illustratively, the computer program 72 may be partitioned into one or more modules/units, which are stored in the memory 71 and executed by the processor 70 to accomplish the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 72 in the terminal 7. For example, the computer program 72 may be divided into the modules 61 to 63 shown in fig. 6.
The terminal 7 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal 7 may include, but is not limited to, a processor 70, a memory 71. It will be appreciated by those skilled in the art that fig. 7 is only an example of a terminal 7 and does not constitute a limitation of the terminal 7, and may include more or less components than those shown, or some components may be combined, or different components, for example, the terminal may also include input output devices, network access devices, buses, etc.
The Processor 70 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 71 may be an internal storage unit of the terminal 7, such as a hard disk or a memory of the terminal 7. The memory 71 may also be an external storage device of the terminal 7, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) and the like provided on the terminal 7. Further, the memory 71 may also include both an internal storage unit and an external storage device of the terminal 7. The memory 71 is used for storing the computer program and other programs and data required by the terminal. The memory 71 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the description of each embodiment has its own emphasis, and reference may be made to the related description of other embodiments for parts that are not described or recited in any embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/terminal and method may be implemented in other ways. For example, the above-described apparatus/terminal embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated module/unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of the embodiments of the method for diagnosing the fault of the wellbore device can be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U.S. disk, removable hard disk, magnetic diskette, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signal, telecommunications signal, and software distribution medium, etc. It should be noted that the computer readable medium may contain suitable additions or subtractions depending on the requirements of legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media may not include electrical carrier signals or telecommunication signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. A method of diagnosing a failure of a wellbore device, comprising:
collecting vibration audio data of shaft equipment;
extracting audio features from the vibration audio data based on a voiceprint recognition model, and judging feature types of the audio features, wherein the feature types comprise normal features and abnormal features, the voiceprint recognition model comprises a feature extraction model and an abnormal judgment model, the feature extraction model is obtained based on fusion of an LSTM neural network and a residual error network, and the abnormal judgment model is obtained based on construction of a Gaussian mixture model;
and if the audio features are abnormal features, determining the fault type corresponding to the audio features based on a fault judgment model.
2. The method of claim 1, wherein the collecting vibration audio data of the wellbore equipment comprises:
and acquiring vibration audio data of the shaft equipment through a distributed optical fiber.
3. The method of diagnosing a malfunction of a wellbore apparatus of claim 2, wherein the vibration audio data further includes position data of a hoist container, the method further comprising:
and outputting alarm information of the vibration audio data, wherein the alarm information comprises an alarm type and corresponding position data.
4. The wellbore equipment fault diagnosis method according to claim 1, wherein the extracting audio features from the vibration audio data based on a voiceprint recognition model and the determining the feature type of the audio features comprises:
calculating the vibration audio data by adopting a Mel frequency cepstrum coefficient to obtain a time sequence audio signal;
and extracting audio features from the time-series audio signal based on the feature extraction model, and judging the feature type of the audio features based on the abnormity judgment model.
5. The method of diagnosing wellbore equipment failure of claim 4, wherein the voiceprint recognition model training process comprises:
carrying out fusion connection on the LSTM neural network and the residual error network;
taking a time series audio signal as input, taking audio features corresponding to the time series audio signal as output, and training the LSTM neural network and the residual error network after fusion connection to obtain a feature extraction model;
and training an abnormity judgment model constructed based on a Gaussian mixture model by taking the audio feature vector as input and taking the feature type corresponding to the audio feature as output to obtain the abnormity judgment model.
6. The wellbore equipment failure diagnostic method of claim 1, wherein the failure determination model training process comprises:
acquiring abnormal characteristics of fault audio of a determined fault type, taking the abnormal characteristics as a training sample, and taking a fault type corresponding to the abnormal characteristics as a label of the training sample, wherein the fault type comprises screw looseness and track abnormity;
and training the VGG network by adopting the training samples to obtain a fault judgment model.
7. The method of claim 1, wherein after the extracting audio features from the vibration audio data based on the voiceprint recognition model, the method further comprises:
clustering the audio features and historical audio features of the wellbore equipment, and judging whether the distance between the audio features and the clustering center is greater than a preset deviation;
and if the distance between the audio features and the clustering center is greater than a preset deviation, sending an early warning prompt by a distributed optical fiber connection optical fiber interception early warning host, wherein the early warning prompt is used for analyzing dangerous factors existing in the shaft equipment and reminding a user of maintaining the shaft equipment in time.
8. A wellbore equipment failure diagnostic apparatus, comprising:
the acquisition module is used for acquiring vibration audio data of the shaft equipment;
the identification module is used for extracting audio features from the vibration audio data and judging the feature types of the audio features based on a voiceprint identification model, wherein the feature types comprise normal features and abnormal features, the voiceprint identification model comprises a feature extraction model and an abnormal judgment model, the feature extraction model is obtained by fusing an LSTM neural network and a residual error network, and the abnormal judgment model is obtained by constructing a Gaussian mixture model;
and the determining module is used for determining the fault type corresponding to the audio feature based on a fault judgment model if the audio feature is an abnormal feature.
9. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the method of diagnosing a failure of a wellbore device as in any one of claims 1-7 above.
10. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the method of diagnosing a failure of a wellbore apparatus as recited in any one of claims 1-7 above.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211384592.2A CN115711669A (en) | 2022-11-07 | 2022-11-07 | Method, device, terminal and storage medium for diagnosing faults of shaft equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211384592.2A CN115711669A (en) | 2022-11-07 | 2022-11-07 | Method, device, terminal and storage medium for diagnosing faults of shaft equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115711669A true CN115711669A (en) | 2023-02-24 |
Family
ID=85232310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211384592.2A Pending CN115711669A (en) | 2022-11-07 | 2022-11-07 | Method, device, terminal and storage medium for diagnosing faults of shaft equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115711669A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115962730A (en) * | 2023-03-16 | 2023-04-14 | 石家庄宜中机电技术有限公司 | Coal mine tunnel roof deformation dense grating on-line monitoring device |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0572026A (en) * | 1991-09-18 | 1993-03-23 | Hitachi Ltd | Apparatus and method for diagnosing fault of equipment in rotary system |
| JP2001108518A (en) * | 1999-08-03 | 2001-04-20 | Mitsui Eng & Shipbuild Co Ltd | Abnormality detecting method and device |
| CN102562158A (en) * | 2010-12-24 | 2012-07-11 | 上海杰蜀光电科技有限公司 | Intrinsically-safe distributed all-fiber downhole monitoring system |
| CN110344816A (en) * | 2019-07-16 | 2019-10-18 | 中国石油大学(华东) | A kind of sand production of oil-gas wells monitoring method based on the monitoring of distribution type fiber-optic sound |
| CN111997600A (en) * | 2020-09-24 | 2020-11-27 | 西南石油大学 | Distributed optical fiber acoustic vibration (DAS) based wellbore fluid flow velocity and flow state monitoring simulation experiment device and method |
| CN112289341A (en) * | 2020-11-03 | 2021-01-29 | 国网智能科技股份有限公司 | Sound abnormity identification method and system for transformer substation equipment |
| CN112483076A (en) * | 2019-09-11 | 2021-03-12 | 中国石油化工股份有限公司 | System for be used for discerning drilling construction complex situation |
| CN113404540A (en) * | 2021-06-11 | 2021-09-17 | 安徽中科昊音智能科技有限公司 | Voiceprint comprehensive monitoring system applied to coal mine scene |
| CN114067829A (en) * | 2021-10-21 | 2022-02-18 | 佳源科技股份有限公司 | Reactor fault diagnosis method and device, computer equipment and storage medium |
| CN114859269A (en) * | 2022-05-13 | 2022-08-05 | 杭州巨骐信息科技股份有限公司 | Cable fault diagnosis method based on voiceprint recognition technology |
| CN115270860A (en) * | 2022-07-18 | 2022-11-01 | 国网信息通信产业集团有限公司 | Transformer abnormity diagnosis method, system and diagnosis equipment |
-
2022
- 2022-11-07 CN CN202211384592.2A patent/CN115711669A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0572026A (en) * | 1991-09-18 | 1993-03-23 | Hitachi Ltd | Apparatus and method for diagnosing fault of equipment in rotary system |
| JP2001108518A (en) * | 1999-08-03 | 2001-04-20 | Mitsui Eng & Shipbuild Co Ltd | Abnormality detecting method and device |
| CN102562158A (en) * | 2010-12-24 | 2012-07-11 | 上海杰蜀光电科技有限公司 | Intrinsically-safe distributed all-fiber downhole monitoring system |
| CN110344816A (en) * | 2019-07-16 | 2019-10-18 | 中国石油大学(华东) | A kind of sand production of oil-gas wells monitoring method based on the monitoring of distribution type fiber-optic sound |
| CN112483076A (en) * | 2019-09-11 | 2021-03-12 | 中国石油化工股份有限公司 | System for be used for discerning drilling construction complex situation |
| CN111997600A (en) * | 2020-09-24 | 2020-11-27 | 西南石油大学 | Distributed optical fiber acoustic vibration (DAS) based wellbore fluid flow velocity and flow state monitoring simulation experiment device and method |
| CN112289341A (en) * | 2020-11-03 | 2021-01-29 | 国网智能科技股份有限公司 | Sound abnormity identification method and system for transformer substation equipment |
| CN113404540A (en) * | 2021-06-11 | 2021-09-17 | 安徽中科昊音智能科技有限公司 | Voiceprint comprehensive monitoring system applied to coal mine scene |
| CN114067829A (en) * | 2021-10-21 | 2022-02-18 | 佳源科技股份有限公司 | Reactor fault diagnosis method and device, computer equipment and storage medium |
| CN114859269A (en) * | 2022-05-13 | 2022-08-05 | 杭州巨骐信息科技股份有限公司 | Cable fault diagnosis method based on voiceprint recognition technology |
| CN115270860A (en) * | 2022-07-18 | 2022-11-01 | 国网信息通信产业集团有限公司 | Transformer abnormity diagnosis method, system and diagnosis equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115962730A (en) * | 2023-03-16 | 2023-04-14 | 石家庄宜中机电技术有限公司 | Coal mine tunnel roof deformation dense grating on-line monitoring device |
| CN115962730B (en) * | 2023-03-16 | 2023-05-12 | 石家庄宜中机电技术有限公司 | On-line monitoring device for deformation dense grating of coal mine tunnel roof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| CN113469060A (en) | Multi-sensor fusion convolution neural network aeroengine bearing fault diagnosis method | |
| CN109901537A (en) | Mechanical equipment method for monitoring operation states and system for edge calculations side | |
| CN113124929A (en) | Transformer substation multi-parameter signal acquisition comprehensive analysis system and method | |
| CN112288021B (en) | Medical wastewater monitoring data quality control method, device and system | |
| CN111141517B (en) | Fan fault diagnosis method and system | |
| DE102018204135A1 (en) | Learning Model Construction Device, Abnormality Detection Device, Abnormality Detection System and Server | |
| CN115711669A (en) | Method, device, terminal and storage medium for diagnosing faults of shaft equipment | |
| KR102405924B1 (en) | A SYSTEM AND METHOD FOR RISK ALARMS USING IoT TIME SERIES TUNNEL DATA AND DATA AUGMENTATION AND DEEP LEARNING ETC | |
| WO2019107315A1 (en) | Method and system for detecting symptom of abnormality in apparatus being monitored | |
| CN115524002B (en) | Operation state early warning method, system and storage medium of power plant rotating equipment | |
| CN111504647A (en) | AR-MSET-based performance degradation evaluation method for rolling bearing | |
| CN115215215A (en) | Intelligent early warning and fault diagnosis method for large-scale gantry shipbuilding crane | |
| CN116778964A (en) | Power transformation equipment fault monitoring system and method based on voiceprint recognition | |
| Pham‐Bao et al. | Energy dissipation‐based material deterioration assessment using random decrement technique and convolutional neural network: A case study of Saigon bridge in Ho Chi Minh City, Vietnam | |
| CN116660761B (en) | Lithium ion battery detection method and system | |
| CN116754022B (en) | On-line detection emergency early warning method and system for cable tunnel | |
| CN116911596A (en) | Worker risk early warning method and system based on operation stability model | |
| CN116822352A (en) | GRNN neural network-based underground waterproof sealing wall working condition prediction method and system | |
| CN114492636B (en) | Transformer winding state signal acquisition system | |
| US20230024104A1 (en) | Identification of false transformer humming using machine learning | |
| Kang et al. | Continuous hidden Markov model based gear fault diagnosis and incipient fault detection | |
| CN114897225A (en) | Accident prediction method and device for drilling operation, electronic device and storage medium | |
| CN114623799A (en) | Structural health monitoring data abnormity early warning method, system, device and storage medium | |
| JP2019191880A (en) | Equipment management support system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |