CN113327629A - Power equipment sound diagnosis method and system - Google Patents

Power equipment sound diagnosis method and system Download PDF

Info

Publication number
CN113327629A
CN113327629A CN202110488447.8A CN202110488447A CN113327629A CN 113327629 A CN113327629 A CN 113327629A CN 202110488447 A CN202110488447 A CN 202110488447A CN 113327629 A CN113327629 A CN 113327629A
Authority
CN
China
Prior art keywords
sound
power equipment
equipment
field
frequency spectrum
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
Application number
CN202110488447.8A
Other languages
Chinese (zh)
Inventor
胡赵宇
李喆
孙汉文
王荣昊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Jiaotong University
Original Assignee
Shanghai Jiaotong University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Jiaotong University filed Critical Shanghai Jiaotong University
Priority to CN202110488447.8A priority Critical patent/CN113327629A/en
Publication of CN113327629A publication Critical patent/CN113327629A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B70/00—Technologies for an efficient end-user side electric power management and consumption
    • Y02B70/30—Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
    • Y04S20/20—End-user application control systems
    • Y04S20/242—Home appliances

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • General Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)

Abstract

The invention provides a sound diagnosis method and a sound diagnosis system for electric equipment, wherein the sound diagnosis method comprises the following steps: acquiring sound of the electrical equipment; carrying out digital signal processing on the acquired sound of the electric power equipment, and extracting the spectral feature of the sound of the electric power equipment; carrying out sound type labeling on the obtained sound of the electric equipment to obtain labeling information; training to obtain a sound classification model by using the spectral characteristics of the sound of the electric power equipment and the labeling information; acquiring field sound of power equipment, performing digital signal processing on the field sound, and extracting spectral characteristics of the field sound; and inputting the frequency spectrum characteristics of the field sound into the sound classification model, acquiring the type of the field sound, and further judging the running state of the power equipment. The invention reduces the monitoring cost in an automatic mode, improves the monitoring efficiency and provides a new solution for monitoring the running state of the power equipment for a long time.

Description

Power equipment sound diagnosis method and system
Technical Field
The invention relates to the technical field of power equipment monitoring, in particular to a power equipment sound diagnosis method and system with edge computing capability.
Background
For the power industry, equipment management is a very important task, and is directly related to the stability of equipment operation. In recent years, the scale of the power grid in China is continuously enlarged, which increases the management difficulty of equipment to a certain extent. Most of the power equipment needs to operate uninterruptedly for a long time, so that faults are inevitable, and when the power equipment fails, the operation of a power system and a power grid is affected, so that the fault detection needs to be performed on the power equipment at regular time.
In the power industry, a traditional power equipment detection mode usually adopts a mode of monitoring physical quantities such as voltage, current and oil chromatography of power equipment to prejudge equipment faults, and the mode is expensive, large in size, complex in installation, and low in intelligence degree, and monitors and diagnoses the power equipment, so that the power equipment is often monitored by equipment with a complex structure and high price, or a large amount of manpower is needed for carrying out patrol inspection at regular time, and therefore the problems that fault analysis is difficult, the work of the equipment is influenced in a detection process, the working efficiency is low and the like exist, and the power equipment cannot be monitored for a long time are solved. .
At present, no explanation or report of the similar technology of the invention is found, and similar data at home and abroad are not collected.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a method and a system for diagnosing the sound of the electric equipment with edge computing capability.
According to an aspect of the present invention, there is provided a power equipment sound diagnosis method including:
acquiring sound of the electrical equipment;
carrying out digital signal processing on the acquired sound of the electric power equipment, and extracting the spectral feature of the sound of the electric power equipment;
carrying out sound type labeling on the obtained sound of the electric equipment to obtain labeling information;
training to obtain a sound classification model by using the spectral characteristics of the sound of the electric power equipment and the labeling information;
acquiring field sound of power equipment, performing digital signal processing on the field sound, and extracting spectral characteristics of the field sound;
and inputting the frequency spectrum characteristics of the field sound into the sound classification model, acquiring the type of the field sound, and further judging the running state of the power equipment.
Preferably, the digital signal processing comprises: pre-emphasis, framing, windowing, fast fourier transform, mel filter bank and discrete cosine transform, converting the sound signal into a frequency spectrum signal.
Preferably, the method further comprises:
and storing the judgment result and the corresponding frequency spectrum characteristic data of the live sound.
Preferably, the method further comprises:
and when the running state of the power equipment is a fault, sending out an early warning report.
Preferably, the method further comprises:
and displaying the running state of the power equipment.
Preferably, the method further comprises:
and updating the sound classification model by using the stored judgment result and the stored frequency spectrum characteristic data of the live sound.
According to another aspect of the present invention, there is provided an electrical equipment sound diagnostic system, comprising, integrated at an edge device side:
the sound acquisition module is used for acquiring the sound of the electric power equipment as a sample and the field sound of the electric power equipment needing to be judged;
the sound signal processing module is used for carrying out digital signal processing on the acquired electric equipment sound and the acquired electric equipment field sound and extracting the frequency spectrum characteristics of the electric equipment sound and the electric equipment field sound; meanwhile, carrying out sound type labeling on the acquired sound of the electrical equipment to obtain labeling information;
and the operation state judgment module is used for training to obtain a sound classification model by using the frequency spectrum characteristics of the sound of the power equipment and the labeling information, and obtaining the type of the field sound by using the sound classification model so as to judge the operation state of the power equipment.
Preferably, the system further comprises, integrated on the server side:
and the display module is used for displaying the running state of the power equipment.
Preferably, the system further comprises, integrated on the server side:
and the storage module is used for storing the judgment result and the corresponding frequency spectrum characteristic data of the field sound.
Preferably, the system further comprises, integrated on the server side:
and the updating module is used for updating the sound classification model by utilizing the stored judgment result and the stored frequency spectrum characteristic data of the live sound.
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following beneficial effects:
the method and the system for sound diagnosis of the electric power equipment have edge computing capability, extract audio features by using a digital signal processing technology, classify the audio features by using a machine learning model and have self-learning capability.
According to the method and the system for diagnosing the sound of the power equipment, provided by the invention, the monitoring cost is reduced, the monitoring efficiency is improved and a new solution is provided for monitoring the running state of the power equipment for a long time by an automatic mode of recording the sound of the power equipment in real time, automatically judging the sound type by using a machine learning model and finally uploading the sound type to a server for storage and visual display.
According to the sound diagnosis method and system for the power equipment, the iterative sound classification model is updated by using the historical data, so that the accuracy of the sound classification model is continuously improved.
The method and the system for diagnosing the sound of the power equipment provided by the invention have the advantages of small occupied area, small interference, low cost and the like by directly monitoring the power equipment through the sound.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
fig. 1 is a flowchart of a sound diagnosis method for an electrical device according to an embodiment of the present invention.
Fig. 2 is a flow chart of a sound diagnosis method for an electric power device according to a preferred embodiment of the present invention.
FIG. 3 is a flow chart of the training of the voice classification model according to a preferred embodiment of the present invention.
Fig. 4 is a schematic structural diagram of a sound diagnostic system of an electrical device according to an embodiment of the present invention.
Detailed Description
The following examples illustrate the invention in detail: the embodiment is implemented on the premise of the technical scheme of the invention, and a detailed implementation mode and a specific operation process are given. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention.
Fig. 1 is a flowchart of a sound diagnosis method for an electrical device according to an embodiment of the present invention.
As shown in fig. 1, the sound diagnosis method for the power equipment provided by this embodiment may include the following steps:
s100, acquiring sound of the electrical equipment;
s200, performing digital signal processing on the acquired electric equipment sound, and extracting the frequency spectrum characteristics of the electric equipment sound;
s300, carrying out sound type marking on the acquired sound of the electric equipment to obtain marking information;
s400, training to obtain a sound classification model by using the spectral characteristics of the sound of the electric power equipment and the labeling information;
s500, acquiring field sound of the power equipment, performing digital signal processing on the field sound, and extracting spectral features of the field sound;
s600, inputting the frequency spectrum characteristics of the field sound into the sound classification model, obtaining the type of the field sound, and further judging the running state of the power equipment.
In step S200, as a preferred embodiment, the digital signal processing may include: pre-emphasis, framing, windowing, fast fourier transform, mel filter bank and discrete cosine transform, converting the sound signal into a frequency spectrum signal.
In this embodiment, as a preferred embodiment, the following steps may be further included:
and S700, storing the judgment result and the corresponding frequency spectrum characteristic data of the live sound.
In this embodiment, as a preferred embodiment, the following steps may be further included:
and S800, when the running state of the power equipment is a fault, sending out an early warning report.
In this embodiment, as a preferred embodiment, the following steps may be further included:
and S900, displaying the running state of the power equipment.
In this embodiment, as a preferred embodiment, the following steps may be further included:
SA00, updating the sound classification model using the stored determination result and spectral feature data of live sound.
Fig. 2 is a flowchart of a sound diagnosis method for an electrical device according to a preferred embodiment of the present invention.
As shown in fig. 2, the sound diagnosis method for electric power equipment provided by the preferred embodiment may include the following steps:
step 1, constructing a pre-trained sound classification model, as shown in fig. 3, which may include the following steps:
step 1.1, collecting sounds of power equipment in different states in a laboratory, and marking the types of the sounds; then, processing the sound into a spectrogram through digital signal processing, training an initial classification model by taking the spectrogram and the marked data as training data, and constructing to obtain a sound classification model;
step 2, periodically collecting sound by using edge equipment;
step 3, performing digital signal processing on the sound, such as pre-emphasis, framing, windowing, Fast Fourier Transform (FFT), Mel filter bank, Discrete Cosine Transform (DCT) and the like, so as to obtain the frequency spectrum characteristics of the audio;
and 4, inputting the frequency spectrum signal of the sound into the pre-trained model to obtain a corresponding classification result, and completing the diagnosis of the sound of the electric power equipment.
As a preferred embodiment, the method can further comprise the following steps:
step 4, judging the obtained result, if the result is a fault signal of the equipment, sending an early warning signal to inform corresponding personnel, and uploading the result and sound to a server; if the device is working properly, the results and sound are uploaded directly to the server.
As a preferred embodiment, the method can further comprise the following steps:
and 5, visually displaying the result through a front-end interface by the server.
As a preferred embodiment, the method can further comprise the following steps:
and 6, training the model according to the stored data by the server side periodically, and updating the model in the edge device side through the network.
In some embodiments of the invention:
the method provided by the embodiment comprises the following steps: the method comprises the steps of collecting field sounds (sound signals can be collected through a sound collection module), carrying out digital signal processing on the sounds, training a sound classification model (classification models in various forms such as SVM and the like can be adopted), classifying the sounds, and sending obtained classification results and samples to a server for storage. The server can perform remote operation on the edge computing device according to the existing program or the operation of the user, such as updating the model.
All steps in the sound diagnosis technology of the electrical equipment are integrated, including the acquisition of samples and the training and updating of models, and the steps are finished in an automatic mode, so that the operation is simplified. Wherein:
the acquisition and identification of the sample can be realized by a timing recording program and an algorithm program of the sensor terminal;
the obtained sound sample and the detection result can be transmitted through a network communication program of the sensor and the server;
the server side can train and update the existing model according to the newly received sample;
the new algorithm model can be deployed to the sensor terminal through network communication.
The sound signals are converted into (MFCC) frequency spectrum signals by utilizing technologies such as pre-emphasis, framing, windowing, Fast Fourier Transform (FFT), Mel filter bank, Discrete Cosine Transform (DCT) and the like, and the features can be conveniently extracted from the audio by a subsequent classification model.
The server end can establish effective network connection with the edge device end, automatically or manually send instructions to the edge device end, and can detect the state of the edge device end and reflect the state on a user interface.
Fig. 4 is a schematic structural diagram of a sound diagnostic system of an electrical device according to an embodiment of the present invention.
As shown in fig. 4, the power equipment sound diagnosis system provided by this embodiment may include: the device comprises a sound acquisition module, a sound signal processing module and an operation state judgment module which are integrated at an edge device end. Wherein:
the sound acquisition module is used for acquiring the sound of the electric power equipment as a sample and the field sound of the electric power equipment needing to be judged;
the sound signal processing module is used for carrying out digital signal processing on the acquired electric equipment sound and the acquired electric equipment field sound and extracting the frequency spectrum characteristics of the electric equipment sound and the electric equipment field sound; meanwhile, carrying out sound type labeling on the acquired sound of the electrical equipment to obtain labeling information;
and the operation state judgment module is used for training to obtain a sound classification model by using the frequency spectrum characteristics of the sound of the power equipment and the labeling information, and obtaining the type of the field sound by using the sound classification model so as to judge the operation state of the power equipment.
In this embodiment, as a preferred embodiment, the following modules integrated at the server end may also be included:
and the display module is used for displaying the running state of the power equipment.
In this embodiment, as a preferred embodiment, the following modules integrated at the server end may also be included:
and the storage module is used for storing the judgment result and the corresponding frequency spectrum characteristic data of the field sound.
In this embodiment, as a preferred embodiment, the following modules integrated at the server end may also be included:
and the updating module is used for updating the sound classification model by utilizing the stored judgment result and the stored frequency spectrum characteristic data of the live sound.
In some embodiments of the invention:
the system integrates the functional modules of sound acquisition, edge calculation, sound signal processing, machine learning such as SVM and the like, front-end user interface display, server-end background operation and the like. The voice collection module collects voice of the power equipment, the MFCC frequency spectrum of the power equipment is obtained through the voice digital signal processing means, the MFCC frequency spectrum is classified according to the type of the voice through classification models such as an SVM and the like, and therefore the fault of the power equipment is diagnosed. In order to improve the real-time performance and reliability of diagnosis, sound collection, processing and classification are carried out at an edge device end, and results and samples are returned to a server end; in order to improve the accuracy of the algorithm, the server side updates the classification model according to the result and the sample fed back by the edge equipment side, and periodically updates the classification model of the edge equipment.
The edge device end main body is a raspberry group, is popular open source hardware, has enough computing power and an external interface, achieves a sound collection function through the plug-in microphone module, and achieves network communication with the server end through the communication module.
The sound signal processing module adopts a classical audio processing means, including pre-emphasis, framing, windowing, Fast Fourier Transform (FFT), mel filter bank, Discrete Cosine Transform (DCT) and the like, so as to obtain the spectral characteristics of the audio.
The sound classification model may adopt an SVM model, which is a classical machine learning model for performing classification processing on the audio signal. The SVM model is pre-trained using laboratory data and then continuously updated based on actual data.
The display module is used as a front-end user interface functional module, provides a visual interface for user operation and viewing, and facilitates interaction between a user and equipment.
The storage module and the updating module are used as a server-side background running function module, and can realize communication, audio and result storage and classification model updating training between the server side and the edge device side.
The method and the system for diagnosing the sound of the electrical equipment provided by the embodiment of the invention have edge computing capability and integrate all steps of diagnosing the sound of the electrical equipment in the monitoring of the electrical equipment. Firstly, a sound collection module at the edge equipment end collects sound of the power equipment, a sound signal processing module obtains an MFCC frequency spectrum of the sound through digital signal processing means such as an FFT algorithm and a filter, and then the MFCC frequency spectrum is classified according to the type of the sound through sound classification models such as an SVM, so that the fault diagnosis of the power equipment is realized. According to the method and the system provided by the embodiment of the invention, the collection, processing and classification of the sound are carried out at the edge side, and the result and the sample are returned to the server side, so that the real-time performance and the reliability of diagnosis are improved; the server side updates the classification model according to the result and the sample fed back by the edge equipment side, and periodically updates the classification model of the edge equipment side, so that the diagnosis accuracy is improved.
It should be noted that, the steps in the method provided by the present invention may be implemented by using corresponding modules, devices, units, and the like in the system, and those skilled in the art may implement the composition of the system by referring to the technical solution of the method, that is, the embodiment in the method may be understood as a preferred example for constructing the system, and will not be described herein again.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes and modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention.

Claims (10)

1. An electrical equipment sound diagnostic method, comprising:
acquiring sound of the electrical equipment;
carrying out digital signal processing on the acquired sound of the electric power equipment, and extracting the spectral feature of the sound of the electric power equipment;
carrying out sound type labeling on the obtained sound of the electric equipment to obtain labeling information;
training to obtain a sound classification model by using the spectral characteristics of the sound of the electric power equipment and the labeling information;
acquiring field sound of power equipment, performing digital signal processing on the field sound, and extracting spectral characteristics of the field sound;
and inputting the frequency spectrum characteristics of the field sound into the sound classification model, acquiring the type of the field sound, and further judging the running state of the power equipment.
2. The power equipment sound diagnostic method according to claim 1, wherein the digital signal processing includes: pre-emphasis, framing, windowing, fast fourier transform, mel filter bank and discrete cosine transform, converting the sound signal into a frequency spectrum signal.
3. The electric power equipment sound diagnostic method according to claim 1 or 2, characterized by further comprising:
and storing the judgment result and the corresponding frequency spectrum characteristic data of the live sound.
4. The electric power equipment sound diagnostic method according to claim 1 or 2, characterized by further comprising:
and when the running state of the power equipment is a fault, sending out an early warning report.
5. The electric power equipment sound diagnostic method according to claim 1 or 2, characterized by further comprising:
and displaying the running state of the power equipment.
6. The electrical equipment sound diagnostic method of claim 3, further comprising:
and updating the sound classification model by using the stored judgment result and the stored frequency spectrum characteristic data of the live sound.
7. An electrical equipment sound diagnostic system, comprising integrated at an edge device end:
the sound acquisition module is used for acquiring the sound of the electric power equipment as a sample and the field sound of the electric power equipment needing to be judged;
the sound signal processing module is used for carrying out digital signal processing on the acquired electric equipment sound and the acquired electric equipment field sound and extracting the frequency spectrum characteristics of the electric equipment sound and the electric equipment field sound; meanwhile, carrying out sound type labeling on the acquired sound of the electrical equipment to obtain labeling information;
and the operation state judgment module is used for training to obtain a sound classification model by using the frequency spectrum characteristics of the sound of the power equipment and the labeling information, and obtaining the type of the field sound by using the sound classification model so as to judge the operation state of the power equipment.
8. The electrical equipment sound diagnostic system of claim 7, further comprising, integrated on the server side:
and the display module is used for displaying the running state of the power equipment.
9. The electrical equipment sound diagnostic system of claim 7, further comprising, integrated on the server side:
and the storage module is used for storing the judgment result and the corresponding frequency spectrum characteristic data of the field sound.
10. The electrical equipment sound diagnostic system of claim 7, further comprising, integrated on the server side:
and the updating module is used for updating the sound classification model by utilizing the stored judgment result and the stored frequency spectrum characteristic data of the live sound.
CN202110488447.8A 2021-05-06 2021-05-06 Power equipment sound diagnosis method and system Pending CN113327629A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110488447.8A CN113327629A (en) 2021-05-06 2021-05-06 Power equipment sound diagnosis method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110488447.8A CN113327629A (en) 2021-05-06 2021-05-06 Power equipment sound diagnosis method and system

Publications (1)

Publication Number Publication Date
CN113327629A true CN113327629A (en) 2021-08-31

Family

ID=77414211

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110488447.8A Pending CN113327629A (en) 2021-05-06 2021-05-06 Power equipment sound diagnosis method and system

Country Status (1)

Country Link
CN (1) CN113327629A (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009204808A (en) * 2008-02-27 2009-09-10 Nippon Telegr & Teleph Corp <Ntt> Sound characteristic extracting method, device and program thereof, and recording medium with the program stored
CN109116196A (en) * 2018-07-06 2019-01-01 山东科汇电力自动化股份有限公司 A kind of power cable fault discharging sound intelligent identification Method
CN109473113A (en) * 2018-11-13 2019-03-15 北京物灵智能科技有限公司 A kind of sound identification method and device
CN110490071A (en) * 2019-07-12 2019-11-22 国网上海市电力公司 A kind of substation's Abstraction of Sound Signal Characteristics based on MFCC
CN111341343A (en) * 2020-03-02 2020-06-26 乐鑫信息科技（上海）股份有限公司 Online updating system and method for abnormal sound detection
CN111948487A (en) * 2020-07-17 2020-11-17 国网上海市电力公司 High-voltage power equipment fault diagnosis method and system based on artificial intelligence
CN112435686A (en) * 2020-11-19 2021-03-02 中国南方电网有限责任公司超高压输电公司 Power equipment fault voice recognition method based on data enhancement
CN112735381A (en) * 2020-12-29 2021-04-30 四川虹微技术有限公司 Model updating method and device

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009204808A (en) * 2008-02-27 2009-09-10 Nippon Telegr & Teleph Corp <Ntt> Sound characteristic extracting method, device and program thereof, and recording medium with the program stored
CN109116196A (en) * 2018-07-06 2019-01-01 山东科汇电力自动化股份有限公司 A kind of power cable fault discharging sound intelligent identification Method
CN109473113A (en) * 2018-11-13 2019-03-15 北京物灵智能科技有限公司 A kind of sound identification method and device
CN110490071A (en) * 2019-07-12 2019-11-22 国网上海市电力公司 A kind of substation's Abstraction of Sound Signal Characteristics based on MFCC
CN111341343A (en) * 2020-03-02 2020-06-26 乐鑫信息科技（上海）股份有限公司 Online updating system and method for abnormal sound detection
CN111948487A (en) * 2020-07-17 2020-11-17 国网上海市电力公司 High-voltage power equipment fault diagnosis method and system based on artificial intelligence
CN112435686A (en) * 2020-11-19 2021-03-02 中国南方电网有限责任公司超高压输电公司 Power equipment fault voice recognition method based on data enhancement
CN112735381A (en) * 2020-12-29 2021-04-30 四川虹微技术有限公司 Model updating method and device

Similar Documents

Publication Publication Date Title
CN110398647B (en) Transformer state monitoring method
CN113298134B (en) System and method for remotely and non-contact health monitoring of fan blade based on BPNN
CN113776794A (en) Fault diagnosis method, device and system for embedded edge computing
CN113551765A (en) Sound spectrum analysis and diagnosis method for equipment fault
CN113030723A (en) Alternating current asynchronous motor state monitoring system
CN110632484A (en) ELM-based GIS partial discharge defect diagnosis and classification system and method
CN109580268A (en) A kind of product abnormal sound, abnormal sound intelligent detecting method
CN115618205A (en) Portable voiceprint fault detection system and method
CN114371353A (en) Power equipment abnormity monitoring method and system based on voiceprint recognition
CN112200238A (en) Hard rock tension-shear fracture identification method and device based on sound characteristics
CN115327363A (en) Method for monitoring mechanical characteristics of high-voltage circuit breaker in electrified manner and identifying state of high-voltage circuit breaker in electrified manner
CN116229991A (en) Motor fault diagnosis method based on MFCC voice feature extraction and machine learning
CN111597948A (en) Fault detection and classification method for bearing vibration signals
CN103267652A (en) Intelligent online diagnosis method for early failures of equipment
CN117782198B (en) Highway electromechanical equipment operation monitoring method and system based on cloud edge architecture
CN114739667A (en) Multi-mode information fusion bearing lubrication state monitoring device and method
CN117169639B (en) Product detection method and system for power adapter production
CN117292713A (en) Transformer voiceprint monitoring method and system based on end Bian Yun cooperation
CN114004996A (en) Abnormal sound detection method, abnormal sound detection device, electronic equipment and medium
CN117556359A (en) Power distribution equipment health state evaluation system and method
CN113450827A (en) Equipment abnormal condition voiceprint analysis algorithm based on compressed neural network
CN113483815A (en) Mechanical fault monitoring system based on industrial big data
CN108613820A (en) A kind of online allophone monitoring algorithm for GIS bulk mechanicals defect diagonsis and positioning
CN111456915A (en) Fault diagnosis device and method for internal components of fan engine room
CN113327629A (en) Power equipment sound diagnosis method and 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
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20210831