CN113746891A - Voiceprint monitoring system for power equipment - Google Patents

Voiceprint monitoring system for power equipment Download PDF

Info

Publication number
CN113746891A
CN113746891A CN202110643551.XA CN202110643551A CN113746891A CN 113746891 A CN113746891 A CN 113746891A CN 202110643551 A CN202110643551 A CN 202110643551A CN 113746891 A CN113746891 A CN 113746891A
Authority
CN
China
Prior art keywords
module
voiceprint
information
equipment
monitoring
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
CN202110643551.XA
Other languages
Chinese (zh)
Inventor
刘敏
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.)
Anhui Zhongke Haoyin Intelligent Technology Co ltd
Original Assignee
Anhui Zhongke Haoyin Intelligent Technology Co ltd
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 Anhui Zhongke Haoyin Intelligent Technology Co ltd filed Critical Anhui Zhongke Haoyin Intelligent Technology Co ltd
Priority to CN202110643551.XA priority Critical patent/CN113746891A/en
Publication of CN113746891A publication Critical patent/CN113746891A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
    • H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/26—Visual data mining; Browsing structured data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • 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
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • 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
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification
    • G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification
    • G10L17/22—Interactive procedures; Man-machine interfaces
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering
    • G10L21/0216—Noise filtering characterised by the method used for estimating noise
    • G10L21/0232—Processing in the frequency domain
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
    • G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/52—Network services specially adapted for the location of the user terminal
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/724—User interfaces specially adapted for cordless or mobile telephones
    • H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G06F2218/04—Denoising

Abstract

The invention provides a voiceprint monitoring system of power equipment, which comprises a voiceprint acquisition terminal and a data management terminal, wherein the voiceprint acquisition terminal comprises a scanning module, a parameter setting module, a data acquisition module and an early warning map module which are respectively connected with the data management terminal; the data management terminal comprises a system setting module, a voiceprint monitoring module, a monitoring map module and a monitoring system management module. The cross-channel voiceprint recognition based on the Cmfmc algorithm technology achieves high accuracy of fault detection of the set-up equipment, and in addition, AI, the Internet of things and 5G are integrated in a voiceprint power online monitoring system, so that a new powerful means is provided for online detection of power equipment, 24-hour online detection of main equipment such as a transformer, a switch cabinet and a reactor bus is provided, and various fault states of the main equipment are early warned in time.

Description

Voiceprint monitoring system for power equipment
Technical Field
The invention relates to the technical field of power equipment monitoring and detection, in particular to a voiceprint monitoring system for power equipment.
Background
On-line monitoring of the operation of electrical equipment is an important technical means for ensuring reliable operation. At present, a plurality of state monitoring methods are adopted, but the methods often adopt a contact detection technology, the operation state monitoring method of the high-voltage power equipment is not mature enough at present, and a wide range of interference sources such as corona discharge, impact generated by switch action, partial discharge possibly occurring in adjacent high-voltage electrical equipment and the like exist on site.
The voiceprint signal can be obtained without contacting a power transformer, the working state of the voiceprint signal cannot be influenced, and the voiceprint signal cannot be influenced in high voltage and strong electromagnetic fields.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a voiceprint monitoring system for power equipment to solve the problems in the background art, and the voiceprint recognition technology is applied to noise recognition of a transformer or power equipment, so that a complex noise mechanism is effectively analyzed, different equipment states are recognized, a basis is provided for monitoring the state of the transformer or the power equipment, and the problems in the prior art are solved.
In order to achieve the purpose, the invention is realized by the following technical scheme: the voiceprint monitoring system of the power equipment comprises a voiceprint acquisition terminal and a data management terminal, wherein,
the voiceprint acquisition terminal comprises a scanning module, a parameter setting module, a data acquisition module and an early warning map module which are respectively connected with the data management terminal,
the scanning module is used for establishing an information interaction channel;
the parameter setting module is used for configuring basic information of the voiceprint acquisition terminal;
the data acquisition module is used for acquiring target voiceprint information and obtaining fault type data of the target voiceprint information based on a voiceprint recognition algorithm;
the early warning map module initially loads the power station geographic information stored in the voiceprint acquisition terminal and is linked with the data management terminal to output the power station geographic information where the target voiceprint information is located,
the data management terminal comprises a system setting module, a voiceprint monitoring module, a monitoring map module and a monitoring system management module,
the system setting module is used for carrying out parameter configuration on the power equipment information based on the data management terminal and uploading the acquired fault type data to the data management terminal server so as to execute a voice print monitoring task of the power equipment;
the voiceprint monitoring module is connected with the system setting module and used for establishing editable voiceprint monitoring information according to the fault type data;
the monitoring map module is connected with the system setting module and is used for displaying the geographical information of the power station where the fault type data is located and analyzing and outputting the use state of the geographical information of the power station;
and the monitoring system management module is connected with the system setting module and is used for executing and outputting the voiceprint monitoring system management instruction of the power equipment.
Furthermore, the data management terminal also comprises a voiceprint terminal module, an early warning information configuration module and an inspection management module, wherein,
the voiceprint terminal module is connected with the system setting module and used for operating a voiceprint recognition algorithm and learning and verifying the established voiceprint monitoring information;
the early warning information configuration module is connected with the system setting module and is used for loading and displaying basic early warning information and outputting the early warning information to an external terminal;
and the patrol management module is connected with the system setting module and is used for managing the user information logging in the voiceprint monitoring system of the power equipment.
Further, the system setting module includes:
the power station information module is connected with the voiceprint acquisition terminal and used for managing a power station information module stored in the voiceprint acquisition terminal power station, wherein the power station information comprises power station longitude and latitude, power station name, voltage grade, power station address, power station type, power station area and remark information;
the equipment information module is connected with the voiceprint acquisition terminal and used for managing the voiceprint acquisition monitoring instructions which are stored in the voiceprint acquisition terminal and executed on the power station, wherein the basic information of the equipment comprises equipment number, equipment model, equipment type, manufacturer, voltage level, commissioning time, group number, the power station and remark information;
the parameter setting module is connected with the voiceprint acquisition terminal and is used for configuring basic information of the data management terminal;
and the acquisition setting module is connected with the voiceprint acquisition terminal and is used for managing the acquired basic information of the target voiceprint information, wherein the basic information acquired by the target voiceprint information comprises a time period, a file path, a file name and mark information.
Furthermore, the voiceprint monitoring module comprises an automatic monitoring module, a manual analysis module and a voiceprint learning module.
Further, the monitoring map module comprises a map query module and a 3D display module, wherein,
the map query module is used for checking the map condition of a target area where the target voiceprint is located;
the 3D display module is used for establishing a pie graph to display the basic state of the data management terminal transit server.
Further, the monitoring system management module includes:
the user management module is used for inquiring and editing the current online user basic information of the voiceprint monitoring system of the power equipment;
the role management module is used for configuring roles of the basic user information and loading and displaying the roles;
the department management module is used for classifying and editing the basic information of the user according to the types of departments, and loading and displaying the basic information;
and the notification management module is used for outputting and issuing processing information of the voiceprint monitoring system of the power equipment.
Furthermore, the voiceprint terminal module comprises a terminal acquisition module, an automatic acquisition module, an equipment state module and a log acquisition module.
Further, the early warning information configuration module comprises an early warning setting module and a warning output module, wherein,
the early warning setting module processes information including power equipment id, early warning id, fault name, early warning name, equipment number, equipment model, manufacturer, affiliated power station, commissioning time, group number and fault grade information;
the warning output module outputs information including time, equipment, place, and type of failure information of the failure occurrence.
Further, the patrol inspection management module is composed of a personnel management module, and the specific implementation mode is as follows: recording the patrol name, the patrol job number, the affiliated team, the mobile phone number, the Mac address, the starting point, the ending point, the distribution route and the time information of the online user of the voiceprint monitoring system of the electrical equipment.
Further, the specific implementation of the voiceprint recognition algorithm is as follows:
the method comprises the steps of firstly, collecting noise signals generated during the operation of the power equipment, and preprocessing the noise signals
S1-1, framing the noise signal to obtain the framing relation of the overlapped signal in the noise signal, so as to ensure the continuity between two adjacent frame signals:
M＝n-Lb/[L(1-b)]
in the formula, M is the frame number, n is the length of the noise signal, L is the frame length, and b is the overlapping rate;
s1-2, performing discrete Fourier transform after applying Hamming window to the framing signal based on the windowing function, so as to increase the continuity of two ends of the framing signal, thereby reducing the distortion phenomenon caused by Fourier transform;
second, extracting MFCC feature vectors
S2-1, obtaining a feature vector corresponding to the framing signal based on a cepstrum coefficient of a Mel frequency domain to form a feature vector group, wherein the Mel frequency is a frequency domain transformed according to human auditory perception characteristics: b (h) 25951g (1 h/700);
s2-2, calculating a feature vector corresponding to the framing signal to obtain parameters after filtering of a filter forming Mel filtering in the solving process:
Figure RE-GDA0003340536220000041
wherein p is the number of filters, miTo obtain p filter parameters after filtering, wherein mi
Figure RE-GDA0003340536220000043
Figure RE-GDA0003340536220000044
N is the number of FFT points, X (k) is the FFT of the preprocessed frame signals, Hi (k) is the filter parameter, and the calculation formula of Hi (k) is as follows:
Figure RE-GDA0003340536220000042
B(f[i+1])-B(f[i])＝B(f[i])-B(f[i-1])
wherein f [ i ] is the center frequency of the triangular filter;
s2-3, calculating to obtain miThen, taking logarithm of the frame signal, and then performing discrete cosine transform to obtain an MFCC feature vector of the framing signal;
thirdly, based on the MFCC characteristic vector, carrying out weighted dimensionality reduction optimization to ensure that the noise characteristic of the electrical equipment is accurately obtained
S3-1, self-defining e eigenvectors to form a matrix G, wherein the dimension of each eigenvector is h, and the matrix G represents:
Figure RE-GDA0003340536220000051
s3-2, calculating a correlation matrix R of the matrix G:
R＝GTG/(e-1)
in the formula, T is a parameter and is taken according to different scenes;
s3-3, calculating to obtain the eigenvalue lambda of the correlation matrix R and the corresponding eigenvector mu based on the step S3-2;
s3-4, calculating the variance contribution rate eta based on the step S3-3iAnd cumulative variance contribution η (l):
Figure RE-GDA0003340536220000052
Figure RE-GDA0003340536220000053
and fourthly, training and optimizing based on a cmfmc algorithm to obtain a fault type data fault model where the target voiceprint information is located.
Compared with the prior art, the invention has the beneficial effects that:
the cross-channel voiceprint recognition based on the Cmfmc algorithm technology achieves high accuracy rate of establishing equipment fault detection, and in addition, AI, the Internet of things and the 5G technology are integrated in a voiceprint electric power online monitoring system, so that a new powerful means is provided for online detection of electric equipment, 24-hour online detection of main equipment such as a transformer, a switch cabinet and a reactor bus is provided, and various fault states of the main equipment are early warned in time;
meanwhile, the fault phenomenon in an abnormal state is subjected to artificial intelligence deep learning through real-time display on a large screen of a monitoring center and a mobile phone APP of an inspection worker, a change monitoring curve of the whole life cycle of the equipment is provided for the inspection worker, and auxiliary study and judgment are made for a correct inspection decision.
Drawings
The disclosure of the present invention is illustrated with reference to the accompanying drawings. It is to be understood that the drawings are designed solely for purposes of illustration and not as a definition of the limits of the invention, for which like reference numerals are used to indicate like parts. Wherein:
fig. 1 is a schematic flow chart illustrating an implementation of a voiceprint monitoring system for an electrical device according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a voiceprint monitoring system of an electrical device according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a voiceprint recognition algorithm proposed in an embodiment of the present invention;
fig. 4 is a first implementation scenario when the scanning module initially establishes a data channel with an external terminal according to an embodiment of the present invention;
fig. 5 is a second implementation scenario diagram when the scanning module and the external terminal successfully establish the data channel according to the embodiment of the present invention;
fig. 6 is a schematic view of an implementation scenario when a parameter setting module configures basic information of a voiceprint acquisition terminal according to an embodiment of the present invention;
fig. 7 is a schematic view of an implementation scenario when a data acquisition module acquires target voiceprint information according to an embodiment of the present invention;
fig. 8 is a schematic view of an implementation scenario when the early warning map module initially loads the power station geographic information stored in the voiceprint acquisition terminal according to the embodiment of the present invention;
fig. 9 is a schematic view of an implementation scenario of the system configuration module for building a power station information infrastructure according to an embodiment of the present invention;
fig. 10 is a schematic view of an implementation scenario when the system configuration module performs device information infrastructure according to an embodiment of the present invention;
fig. 11 is a schematic view of an implementation scenario when a system configuration module performs data management terminal parameter information infrastructure according to an embodiment of the present invention;
fig. 12 is a schematic view of an implementation scenario when the system configuration module performs basic construction of voiceprint information collected by the data management terminal according to an embodiment of the present invention;
fig. 13 is a schematic view of an implementation scenario when the voiceprint monitoring module executes an automatic monitoring instruction according to an embodiment of the present invention;
fig. 14 is a schematic view of an implementation scenario when the voiceprint monitoring module executes a voiceprint learning instruction according to an embodiment of the present invention;
fig. 15 is a first schematic view of an implementation scenario when the monitoring map module executes a query instruction of geographic information of a target area according to an embodiment of the present invention;
fig. 16 is a schematic view illustrating a second implementation scenario in which pie-shaped graph analysis is established when the monitoring map module executes a query instruction of geographic information of a target area according to an embodiment of the present invention;
fig. 17 is a schematic view of an implementation scenario when a voiceprint terminal module executes a voiceprint basic acquisition information editing instruction according to an embodiment of the present invention;
fig. 18 is a schematic view of an implementation scenario in which the voiceprint terminal module performs automatic collection of voiceprint basic information and performs an editing instruction according to an embodiment of the present invention;
FIG. 19 is a diagram illustrating an implementation scenario of the device state proposed in an embodiment of the present invention;
fig. 20 is a schematic view of an implementation scenario for collecting and recording a target voiceprint according to an embodiment of the present invention;
fig. 21 is a schematic view of an implementation scenario based on an early warning setting module according to an embodiment of the present invention;
fig. 22 is a schematic view of an implementation scenario for outputting warning information based on a warning output module according to an embodiment of the present invention;
fig. 23 is a schematic view of an implementation scenario in which the patrol management module performs online user patrol management on the voiceprint monitoring system of the electrical device according to an embodiment of the present invention;
fig. 24 is a schematic view of an implementation scenario of performing basic information management editing on-line users of a voiceprint monitoring system of an electrical device based on a monitoring system management module according to an embodiment of the present invention.
Detailed Description
It is easily understood that according to the technical solution of the present invention, a person skilled in the art can propose various alternative structures and implementation ways without changing the spirit of the present invention. Therefore, the following detailed description and the accompanying drawings are merely illustrative of the technical aspects of the present invention, and should not be construed as all of the present invention or as limitations or limitations on the technical aspects of the present invention.
As shown in fig. 1-2, as an embodiment of the present invention, the present invention provides a technical solution: the voiceprint monitoring system of the power equipment comprises a voiceprint acquisition terminal and a data management terminal, wherein,
the voiceprint acquisition terminal comprises a scanning module, a parameter setting module, a data acquisition module and an early warning map module which are respectively connected with the data management terminal,
the scanning module is used for establishing an information interaction channel, and is specifically implemented as shown in fig. 4-5: the user enters the loaded third-party software, after the user enters the app of the third-party software, the default opened interface of the software is the scanning module, and the module has the main functions of scanning available terminals nearby through mobile phone Bluetooth and being connected with corresponding terminals after being manually confirmed by an operator;
the parameter setting module is used for configuring basic information of the voiceprint acquisition terminal, specifically, as shown in fig. 6, based on app of third-party software, a parameter setting area is clicked, the software enters the parameter setting module, and the module has the main function of carrying out detailed preparation work on the next voiceprint acquisition activity, wherein the module comprises a series of parameter settings, such as information of a recording value, a sampling frequency, an FTP user name, an FTP password, an IP address, a port number and the like;
the data acquisition module is used for acquiring target voiceprint information and obtaining fault type data of the target voiceprint information based on a voiceprint recognition algorithm, and in specific implementation, as shown in fig. 7: based on app of third-party software, clicking a lower data acquisition area, and enabling the software to enter a data acquisition module, wherein the module has the main function of acquiring voiceprints;
the early warning map module initially loads the power station geographic information stored in the voiceprint acquisition terminal, and links with the data management terminal to output the power station geographic information where the target voiceprint information is located, and during specific implementation, as shown in fig. 8, based on app of third-party software, a lower early warning map area is clicked, the software enters the early warning map module, and the main functions of the module include: the method comprises the steps that power station information in a database is taken during initialization and is loaded and displayed on a map, the power station information is linked with voiceprint records in the database at any time, an operator is reminded at the first time when a fault is found, and the fault is immediately displayed below a transformer substation icon corresponding to the map with a special warning special effect;
the data management terminal comprises a system setting module, a voiceprint monitoring module, a monitoring map module and a monitoring system management module,
the system setting module is used for carrying out parameter configuration on the power equipment information based on the data management terminal and uploading the acquired fault type data to the data management terminal server so as to execute a voice print monitoring task of the power equipment;
the voiceprint monitoring module is connected with the system setting module and used for establishing editable voiceprint monitoring information according to the fault type data;
the monitoring map module is connected with the system setting module and is used for displaying the geographical information of the power station where the fault type data is located and analyzing and outputting the use state of the geographical information of the power station;
the monitoring system management module is connected with the system setting module and used for executing and outputting a voiceprint monitoring system management instruction of the power equipment.
As shown in fig. 3, in an embodiment of the present invention, a specific implementation manner of the voiceprint recognition algorithm is as follows:
the method comprises the steps of firstly, collecting noise signals generated during the operation of the power equipment, and preprocessing the noise signals
S1-1, framing the noise signal to obtain the framing relation of the overlapped signal in the noise signal, so as to ensure the continuity between two adjacent frame signals:
M＝n-Lb/[L(1-b)]
in the formula, M is the frame number, n is the length of the noise signal, L is the frame length, and b is the overlapping rate;
s1-2, performing discrete Fourier transform after applying Hamming window to the framing signal based on the windowing function, so as to increase the continuity of two ends of the framing signal, thereby reducing the distortion phenomenon caused by Fourier transform;
second, extracting MFCC feature vectors
S2-1, obtaining a feature vector corresponding to the framing signal based on the Mel frequency domain cepstrum coefficient to form a feature vector group, wherein the MFCC coefficient is a Mel frequency domain cepstrum coefficient, and the Mel frequency is a frequency domain transformed according to the human auditory perception characteristic: 25951g (1h/700), wherein the obtaining process comprises FFT, Mel filtering, logarithm transformation and discrete cosine transformation, and the Mel filtering is realized by a filter bank consisting of a plurality of triangular band-pass filters;
s2-2, calculating a feature vector corresponding to the framing signal to obtain the parameters of the filter forming Mel filtering in the solving process:
Figure RE-GDA0003340536220000091
wherein p is the number of filters, miTo obtain p filter parameters after filtering, wherein mi
Figure RE-GDA0003340536220000093
Figure RE-GDA0003340536220000094
N is the number of FFT points, X (k) is the FFT of the preprocessed frame signals, Hi (k) is the filter parameter, and the calculation formula of Hi (k) is as follows:
Figure RE-GDA0003340536220000092
B(f[i+1])-B(f[i])＝B(f[i])-B(f[i-1])
wherein f [ i ] is the center frequency of the triangular filter;
s2-3, after mi is obtained through calculation, discrete cosine transform is carried out on mi after logarithm of mi is taken, and MFCC feature vectors C (i) of the framing signals are obtained;
based on the above concept of the invention, when analyzing the noise signal of the transformer, the higher MFCC feature vector dimension can ensure the sufficient extraction of the noise signal feature, but too high dimension of the feature vector consumes a lot of time, and the computational complexity is increased, so to improve the computational efficiency, the PCA algorithm is adopted to reduce the dimension of the calculated high dimension MFCC feature vector, and simultaneously ensure the accurate acquisition of the noise feature of the transformer:
thirdly, based on the MFCC characteristic vector, carrying out weighted dimensionality reduction optimization to ensure that the noise characteristic of the electrical equipment is accurately obtained
S3-1, self-defining e eigenvectors to form a matrix G, wherein the dimension of each eigenvector is h, and the matrix G represents:
Figure RE-GDA0003340536220000101
s3-2, calculating a correlation matrix R of the matrix G:
R＝GTG/(e-1)
in the formula, T is a parameter and is taken according to different scenes;
s3-3, calculating to obtain the eigenvalue lambda of the correlation matrix R and the corresponding eigenvector mu based on the step S3-2;
s3-4, calculating the variance contribution rate eta based on the step S3-3iAnd cumulative variance contribution η (l):
Figure RE-GDA0003340536220000102
Figure RE-GDA0003340536220000103
fourthly, training and optimizing based on a cmfmc algorithm to obtain a fault type data fault model where the target voiceprint information is located, wherein the fault type table is as follows:
Figure RE-GDA0003340536220000111
as shown in fig. 9-24, as an embodiment of the present invention, the present invention further includes a voiceprint terminal module, an early warning information configuration module, and an inspection management module, wherein,
voiceprint terminal module connected system sets up the module for the voiceprint recognition algorithm of operation and to study, verify with the voiceprint monitoring information who establishes, voiceprint terminal module includes terminal acquisition module, automatic acquisition module, equipment status module and gathers the log module, during concrete implementation:
based on APP of third-party software, on the first hand, a user enters a terminal acquisition module by clicking 'voiceprint terminal' and 'terminal acquisition' under a directory thereof, the module can browse basic information of the existing terminal at present, all the basic information is transmitted from an external terminal APP, new terminal information can be added, and modification and deletion operations can be performed on the existing terminal;
secondly, a user enters an automatic acquisition module by clicking a voiceprint terminal and automatically acquiring the voiceprint terminal in a directory, wherein the module can be a large core module, the user can know basic information of an acquired file, can listen to the acquired voiceprint file and learn the voiceprint file, namely voiceprint registration, the interface can automatically jump to a voiceprint learning menu under voiceprint monitoring after the registration is completed, a new fault name can be set, manual verification is carried out on the existing voiceprint based on a voiceprint verification button, and the interface can automatically jump to an automatic monitoring page after the verification is completed, so that the fault type of the file is judged;
in a third aspect, based on the device status module, the user enters the device status module by clicking the voiceprint terminal and the device status in the directory thereof, the module is used for monitoring the status of the transfer server, and the status of the transfer server comprises a disk usage space, a CPU usage rate, a memory usage and a processor, and an administrator or the user can judge the status of the transfer server through the information;
in the fourth aspect, based on the log collecting module, a user or an administrator enters the log collecting module by clicking the voiceprint terminal and the collected log under the directory of the voiceprint terminal, and the module is used for uploading the monitoring file at a set time interval and displaying the monitoring file;
the early warning information configuration module is connected with the system setting module and is used for loading and displaying the basic early warning information and outputting the early warning information to an external terminal, the early warning information configuration module comprises an early warning setting module and a warning output module, wherein,
based on the first aspect of the technical concept, a user enters an early warning setting module by clicking 'early warning information' and 'early warning setting' under a directory thereof, and processing information of the early warning setting module comprises electric power equipment id, early warning id, fault name, early warning name, equipment number, equipment model, manufacturer, affiliated power station, commissioning time, group number and fault grade information;
based on the second aspect of the technical concept, based on the warning output module, a user enters the warning output module by clicking 'warning information' and 'warning output' under a directory thereof, the warning output module outputs information including time, equipment, place and fault type information of fault occurrence, and when a third-party software APP group follows up, an administrator can click a corresponding button on the page according to the warning output information to issue warning or remove warning to a corresponding mobile phone terminal;
patrol and examine management module connected system and set up the module for user information to logging in power equipment voiceprint monitored control system manages, patrols and examines management module and comprises personnel management module, during concrete implementation: based on the patrol inspection management module, a user enters the personnel management module by clicking 'patrol inspection management' and 'personnel management' under a directory thereof, and records or inspects patrol inspection names, patrol inspection job numbers, affiliated teams, mobile phone numbers, Mac addresses, starting points, finishing points, distribution routes and time information of online users of the voiceprint monitoring system of the power equipment.
As an embodiment of the present invention, the system setting module includes:
be connected with the voiceprint acquisition terminal in order to be used for managing the power station information module that has been stored in voiceprint acquisition terminal power station, during the concrete implementation: based on the app of the third-party software, a user enters a power station information module by clicking 'equipment setting' and 'power station information' in a directory, the module is used by an administrator to manage power station information in a district, basic information of each power station is displayed, the power station information comprises power station longitude and latitude, power station name, voltage level, power station address, power station type, power station area and remark information, and the administrator can add a new power station on the page or modify and delete an existing power station;
be connected with the voiceprint acquisition terminal in order to be used for managing the equipment information module that has been stored in the voiceprint acquisition terminal and to the power station execution voiceprint acquisition monitoring instruction, during the concrete implementation: based on the app of the third-party software, a user or an administrator enters an equipment information module by clicking 'acquisition setting' and 'equipment information' under a catalog thereof, the module is a module used by the administrator to manage the voiceprint monitoring equipment of each region and displays basic information of each equipment, the basic information of the equipment comprises equipment number, equipment model, equipment type, manufacturer, voltage level, commissioning time, group number, affiliated power station and remark information, and the administrator can add new equipment on the page and also can modify and delete the existing equipment;
the parameter setting module is connected with the voiceprint acquisition terminal and used for carrying out basic information configuration on the data management terminal, and during specific implementation: based on app of third-party software, a user enters a parameter setting module by clicking 'acquisition setting' and 'parameter setting' under a directory thereof, the module displays basic information of each parameter configuration, including matching type, time period, group number, recording file path and recording cutting path, an administrator can add the parameter configuration on the page, can modify and delete the set parameter configuration, can apply to one of the parameters, so that the page jumps to an automatic monitoring page, the applied configuration of folders, group numbers and the like in the parameter can be applied to the automatic monitoring, the automatic monitoring page can select whether to automatically refresh by clicking an automatic refresh button, after data obtained after voiceprint analysis is filled in a form, the form changes the style of a corresponding fault line according to voiceprint feedback to prompt, the current monitoring return parameter setting page can be ended by clicking to finish the automatic monitoring;
the acquisition setting module is connected with the voiceprint acquisition terminal and used for managing acquired target voiceprint information basic information, when the method is specifically implemented, a user enters the acquisition setting module by clicking 'terminal setting' and 'acquisition setting' under a directory thereof based on app of third-party software, the module displays basic information of acquired voiceprints, the basic information comprises a time period, a file path, a file name and a mark, an administrator can add acquired files on the page, and the set acquisition setting can be modified and deleted.
As an embodiment of the present invention, the voiceprint monitoring module includes an automatic monitoring module, a manual analysis module and a voiceprint learning module, and when implemented specifically:
on the first hand, a user enters an automatic monitoring module by clicking 'voiceprint monitoring' and 'automatic monitoring' under a directory thereof based on app of third-party software, the module can check monitoring data stored in a database, wherein the monitoring data comprises serial numbers, equipment numbers, power stations to which the user belongs, time periods, collected files, audition files, group numbers, analysis time, voiceprint types and a current state, when the current state has a fault, a form can change the style of a corresponding line according to a specific fault type to prompt, at the moment, the page is not automatically refreshed by default, the page can be refreshed at regular time after clicking an automatic refresh button, the state which is not automatically refreshed can be restored by clicking again, a manager can add new monitoring information into the page, and can modify or delete existing monitoring information;
in the second aspect, a user enters a manual analysis module by clicking 'voiceprint monitoring' and 'manual analysis' under a directory based on app of third-party software, and the module can search audio files according to the file directory and manually select the audio files for analysis;
in the third aspect, a user enters a voiceprint learning module by clicking voiceprint monitoring and voiceprint learning under a directory of the voiceprint monitoring based on the app of third-party software, the module can check fault types including fault types, early warning levels, fault codes, background colors, font colors, registration Ids, packet numbers, file paths and time, and an administrator can add new faults to the page and also can modify or delete existing fault information.
As an embodiment of the present invention, the monitoring map module includes a map query module and a 3D display module, wherein the monitoring map module displays the power station information in a map form by combining with a Baidu map plug-in or a GPS positioning plug-in, and when the monitoring map module is specifically implemented:
on the first hand, based on a map query module, a user or an administrator enters the map query module by clicking a 'monitoring map' and a 'monitoring map' under a directory thereof, the module is mainly used for viewing the map condition of a target area, the map is initialized, the existing power station information is loaded at the corresponding position of the map in the form of an icon, the map can be zoomed by sliding a mouse roller or moving a left tool bar up and down, and the map can be dragged by clicking the left mouse button to press the map or clicking the corresponding button of the left tool bar; clicking a blank position of the map by a right key, selecting addition, and manually adding a power station at a corresponding position; the left key clicks the existing power station icon, and a small prompt of detailed information of the power station can be displayed;
in the second aspect, based on the 3D display module, the user enters the 3D display module by clicking the "monitoring map" and the "3D display" in the directory thereof in the third-party software APP, and the module can display the basic state of the transit server in the form of a pie chart.
As an embodiment of the present invention, the monitoring system management module includes:
the user management module is used for inquiring and editing the current online user basic information of the voiceprint monitoring system of the power equipment;
the role management module is used for configuring roles of the basic information of the user and loading and displaying the roles;
the department management module is used for classifying and editing the basic information of the user according to the types of departments, and loading and displaying the basic information;
the dictionary management module is used for managing the data dictionary information in the background;
the menu management module is used for creating a new dictionary or modifying the existing dictionary;
the log module is used for inquiring the log information of a user or an administrator;
the service log module is used for inquiring the service information of a user or an administrator;
the monitoring management module can perform corresponding monitoring management;
and the notification management module is used for outputting and issuing processing information of the voiceprint monitoring system of the power equipment, and during specific implementation: in a first aspect: a notification is issued to the user, and meanwhile, the user can modify or delete the previously issued notification;
in the second aspect, based on the short message sending module built in the notification management module, the module can send a verification code to the third-party software APP for identity verification.
In one embodiment of the invention, the data acquisition module adopts a HYCG-001 model high-sensitivity voiceprint vibration sensor, and the voiceprint acquisition terminal adopts an HYCJ-08 model eight-path voiceprint acquisition terminal.
In a second embodiment of the present invention, the voiceprint acquisition terminal further includes a voice interface circuit module, a CODEC coding module, a DSP processing module, and an ethernet transport module, and in specific implementation, a user processes an analog voice signal input by a line through the voice interface circuit module, outputs the processed analog voice signal as a digital signal through the CODEC coding module, enters the DSP processing module, performs processing by a DSP algorithm, and then transmits the processed analog voice signal to an FTP server through the ethernet transport module or connects a computer through a USB interface to realize voiceprint monitoring of an electric power device.
In an embodiment of the present invention, the present invention has the following advantages:
the cross-channel voiceprint recognition based on the Cmfmc algorithm technology achieves high accuracy of fault detection of the set-up equipment, and in addition, AI, the Internet of things and 5G are integrated in a voiceprint electric power online monitoring system, so that a new powerful means is provided for online detection of electric power equipment, 24-hour online detection of main equipment such as a transformer, a switch cabinet and a reactor bus is provided, and various fault states of the main equipment are early warned in time;
meanwhile, the fault phenomenon in an abnormal state is subjected to artificial intelligence deep learning through real-time display on a large screen of a monitoring center and a mobile phone APP of an inspection worker, a change monitoring curve of the whole life cycle of the equipment is provided for the inspection worker, and auxiliary study and judgment are made for a correct inspection decision.
The technical scope of the present invention is not limited to the above description, and those skilled in the art can make various changes and modifications to the above-described embodiments without departing from the technical spirit of the present invention, and such changes and modifications should fall within the protective scope of the present invention.

Claims (10)

1. Power equipment voiceprint monitored control system, its characterized in that: comprises a voiceprint acquisition terminal and a data management terminal, wherein,
the voiceprint acquisition terminal comprises a scanning module, a parameter setting module, a data acquisition module and an early warning map module which are respectively connected with the data management terminal,
the scanning module is used for establishing an information interaction channel;
the parameter setting module is used for configuring basic information of the voiceprint acquisition terminal;
the data acquisition module is used for acquiring target voiceprint information and obtaining fault type data of the target voiceprint information based on a voiceprint recognition algorithm;
the early warning map module initially loads the power station geographic information stored in the voiceprint acquisition terminal and is linked with the data management terminal to output the power station geographic information where the target voiceprint information is located,
the data management terminal comprises a system setting module, a voiceprint monitoring module, a monitoring map module and a monitoring system management module,
the system setting module is used for carrying out parameter configuration on the power equipment information based on the data management terminal and uploading the acquired fault type data to the data management terminal server so as to execute a voice print monitoring task of the power equipment;
the voiceprint monitoring module is connected with the system setting module and used for establishing editable voiceprint monitoring information according to the fault type data;
the monitoring map module is connected with the system setting module and is used for displaying the geographical information of the power station where the fault type data is located and analyzing and outputting the use state of the geographical information of the power station;
and the monitoring system management module is connected with the system setting module and is used for executing and outputting the voiceprint monitoring system management instruction of the power equipment.
2. The electrical equipment voiceprint monitoring system of claim 1 wherein: the data management terminal also comprises a voiceprint terminal module, an early warning information configuration module and an inspection management module, wherein,
the voiceprint terminal module is connected with the system setting module and used for operating a voiceprint recognition algorithm and learning and verifying the established voiceprint monitoring information;
the early warning information configuration module is connected with the system setting module and is used for loading and displaying basic early warning information and outputting the early warning information to an external terminal;
and the patrol management module is connected with the system setting module and is used for managing the user information logging in the voiceprint monitoring system of the power equipment.
3. The electrical equipment voiceprint monitoring system of claim 1 wherein: the system setting module includes:
the power station information module is connected with the voiceprint acquisition terminal and used for managing a power station information module stored in the voiceprint acquisition terminal power station, wherein the power station information comprises power station longitude and latitude, power station name, voltage grade, power station address, power station type, power station area and remark information;
the equipment information module is connected with the voiceprint acquisition terminal and used for managing the voiceprint acquisition monitoring instructions which are stored in the voiceprint acquisition terminal and executed on the power station, wherein the basic information of the equipment comprises equipment number, equipment model, equipment type, manufacturer, voltage level, commissioning time, group number, the power station and remark information;
the parameter setting module is connected with the voiceprint acquisition terminal and is used for configuring basic information of the data management terminal;
and the acquisition setting module is connected with the voiceprint acquisition terminal and is used for managing the acquired basic information of the target voiceprint information, wherein the basic information acquired by the target voiceprint information comprises a time period, a file path, a file name and mark information.
4. The electrical equipment voiceprint monitoring system of claim 1 wherein: the voiceprint monitoring module comprises an automatic monitoring module, a manual analysis module and a voiceprint learning module.
5. The electrical equipment voiceprint monitoring system of claim 1 wherein: the monitoring map module comprises a map query module and a 3D display module, wherein,
the map query module is used for checking the map condition of a target area where the target voiceprint is located;
the 3D display module is used for establishing a pie graph to display the basic state of the data management terminal transit server.
6. The electrical equipment voiceprint monitoring system of claim 1 wherein: the monitoring system management module comprises:
the user management module is used for inquiring and editing the current online user basic information of the voiceprint monitoring system of the power equipment;
the role management module is used for configuring roles of the basic user information and loading and displaying the roles;
the department management module is used for classifying and editing the basic information of the user according to the types of departments, and loading and displaying the basic information;
and the notification management module is used for outputting and issuing processing information of the voiceprint monitoring system of the power equipment.
7. The electrical equipment voiceprint monitoring system of claim 2 wherein: the voiceprint terminal module comprises a terminal acquisition module, an automatic acquisition module, an equipment state module and a log acquisition module.
8. The electrical equipment voiceprint monitoring system of claim 2 wherein: the early warning information configuration module comprises an early warning setting module and a warning output module, wherein,
the early warning setting module processes information including power equipment id, early warning id, fault name, early warning name, equipment number, equipment model, manufacturer, affiliated power station, commissioning time, group number and fault grade information;
the warning output module outputs information including time, equipment, place, and type of failure information of the failure occurrence.
9. The electrical equipment voiceprint monitoring system of claim 2 wherein: patrol and examine management module and constitute by personnel management module, concrete implementation mode is: recording the patrol name, the patrol job number, the affiliated team, the mobile phone number, the Mac address, the starting point, the ending point, the distribution route and the time information of the online user of the voiceprint monitoring system of the electrical equipment.
10. The electrical equipment voiceprint monitoring system of claim 1 wherein: the specific implementation mode of the voiceprint recognition algorithm is as follows:
the method comprises the steps of firstly, collecting noise signals generated during the operation of the power equipment, and preprocessing the noise signals
S1-1, framing the noise signal to obtain the framing relation of the overlapped signal in the noise signal, so as to ensure the continuity between two adjacent frame signals:
M＝n-Lb/[L(1-b)]
in the formula, M is the frame number, n is the length of the noise signal, L is the frame length, and b is the overlapping rate;
s1-2, performing discrete Fourier transform after applying Hamming window to the framing signal based on the windowing function, so as to increase the continuity of two ends of the framing signal, thereby reducing the distortion phenomenon caused by Fourier transform;
second, extracting MFCC feature vectors
S2-1, obtaining a feature vector corresponding to the framing signal based on a cepstrum coefficient of a Mel frequency domain to form a feature vector group, wherein the Mel frequency is a frequency domain transformed according to human auditory perception characteristics: b (h) 25951g (1 h/700);
s2-2, calculating a feature vector corresponding to the framing signal to obtain parameters after filtering of a filter forming Mel filtering in the solving process:
Figure RE-FDA0003340536210000031
wherein p is the number of filters, miTo obtain p filter parameters after filtering, wherein mi(i＜＜1，2，
Figure RE-FDA0003340536210000032
P), N is the number of FFT points, x (k) is the FFT of the preprocessed frame signal, hi (k) is the filter parameter, hi (k) is calculated as:
Figure RE-FDA0003340536210000041
B(f[i+1])-B(f[i])＝B(f[i])-B(f[i-1])
wherein f [ i ] is the center frequency of the triangular filter;
s2-3, after mi is obtained through calculation, discrete cosine transform is carried out on mi after logarithm of mi is taken, and MFCC feature vectors of the framing signals are obtained;
thirdly, based on the MFCC characteristic vector, carrying out weighted dimensionality reduction optimization to ensure that the noise characteristic of the electrical equipment is accurately obtained
S3-1, self-defining e eigenvectors to form a matrix G, wherein the dimension of each eigenvector is h, and the matrix G represents:
Figure RE-FDA0003340536210000042
s3-2, calculating a correlation matrix R of the matrix G:
R＝GTG/(e-1)
in the formula, T is a parameter and is taken according to different scenes;
s3-3, calculating the eigenvalue lambda of the correlation matrix R and the corresponding eigenvector based on the step S3-2
Figure RE-FDA0003340536210000053
S3-4, calculating the variance contribution rate eta based on the step S3-3iAnd cumulative variance contribution η (l):
Figure RE-FDA0003340536210000051
Figure RE-FDA0003340536210000052
and fourthly, training and optimizing based on a cmfmc algorithm to obtain a fault type data fault model where the target voiceprint information is located.
CN202110643551.XA 2021-06-09 2021-06-09 Voiceprint monitoring system for power equipment Pending CN113746891A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110643551.XA CN113746891A (en) 2021-06-09 2021-06-09 Voiceprint monitoring system for power equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110643551.XA CN113746891A (en) 2021-06-09 2021-06-09 Voiceprint monitoring system for power equipment

Publications (1)

Publication Number Publication Date
CN113746891A true CN113746891A (en) 2021-12-03

Family

ID=78728429

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110643551.XA Pending CN113746891A (en) 2021-06-09 2021-06-09 Voiceprint monitoring system for power equipment

Country Status (1)

Country Link
CN (1) CN113746891A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114510099A (en) * 2022-02-16 2022-05-17 国网北京市电力公司 Monitoring system
CN115295008A (en) * 2022-07-28 2022-11-04 国网安徽省电力有限公司电力科学研究院 Intelligent fault identification system and method based on voiceprint data
CN115662460A (en) * 2022-12-29 2023-01-31 杭州兆华电子股份有限公司 Abnormal sound extraction method for industrial equipment

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017034751A (en) * 2015-07-29 2017-02-09 東京電力ホールディングス株式会社 Monitoring control system
CN109557412A (en) * 2018-11-27 2019-04-02 华翔翔能电气股份有限公司 A kind of method for recognizing sound-groove and system of transformer fault
CN110412368A (en) * 2019-06-27 2019-11-05 安徽继远软件有限公司 Electrical equipment online supervision method and system based on Application on Voiceprint Recognition
CN111784026A (en) * 2020-05-28 2020-10-16 国网信通亿力科技有限责任公司 Cloud-side cooperative sensing-based all-dimensional physical examination system for electrical equipment of transformer substation
CN112420055A (en) * 2020-09-22 2021-02-26 甘肃同兴智能科技发展有限公司 Substation state identification method and device based on voiceprint characteristics

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017034751A (en) * 2015-07-29 2017-02-09 東京電力ホールディングス株式会社 Monitoring control system
CN109557412A (en) * 2018-11-27 2019-04-02 华翔翔能电气股份有限公司 A kind of method for recognizing sound-groove and system of transformer fault
CN110412368A (en) * 2019-06-27 2019-11-05 安徽继远软件有限公司 Electrical equipment online supervision method and system based on Application on Voiceprint Recognition
CN111784026A (en) * 2020-05-28 2020-10-16 国网信通亿力科技有限责任公司 Cloud-side cooperative sensing-based all-dimensional physical examination system for electrical equipment of transformer substation
CN112420055A (en) * 2020-09-22 2021-02-26 甘肃同兴智能科技发展有限公司 Substation state identification method and device based on voiceprint characteristics

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王丰华等: "基于改进MFCC和VQ的变压器声纹识别模型", 《中国电机工程学报》, pages 2 - 4 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114510099A (en) * 2022-02-16 2022-05-17 国网北京市电力公司 Monitoring system
CN115295008A (en) * 2022-07-28 2022-11-04 国网安徽省电力有限公司电力科学研究院 Intelligent fault identification system and method based on voiceprint data
CN115662460A (en) * 2022-12-29 2023-01-31 杭州兆华电子股份有限公司 Abnormal sound extraction method for industrial equipment

Similar Documents

Publication Publication Date Title
CN113746891A (en) Voiceprint monitoring system for power equipment
CN106771856B (en) Electric power transmission line lightning stroke point determination method based on unmanned aerial vehicle technology
CN113689013A (en) Intelligent monitoring and operation and maintenance system for transformer
CN107819645B (en) Internet of things testing method based on software simulation
CN102761174B (en) Fault intelligent diagnosis and analysis system and method based on dispatching integrated data platform
CN111537830A (en) Power distribution network fault diagnosis method based on cloud edge architecture and wavelet neural network
WO2023216553A1 (en) Multi-fault diagnosis method for power distribution network, and system
CN114723285B (en) Power grid equipment safety evaluation prediction method
CN103901314A (en) Online monitoring device for monitoring power transformer core ground faults and online monitoring method of online monitoring device
CN110837532A (en) Method for detecting electricity stealing behavior of charging pile based on big data platform
CN107085549A (en) The method and apparatus of fault message generation
CN113095708A (en) Power quality analysis system and method based on big data
CN112085233A (en) Power digital information model based on station domain BIM data fusion multi-source information
CN109190716A (en) Processing method, device and the electronic equipment of low-voltage collecting meter reading failure
CN216434700U (en) Intelligent inspection terminal equipment based on Internet of things and positioning technology
CN110503215A (en) Method based on image recognition technology identification equipment state, failure and processing exception
CN115603464B (en) Intelligent generation management system for power grid operation ticket based on digital twin
CN111597227A (en) Electric power automation cloud detection platform and monitoring method based on big data platform technology
CN203798949U (en) Online monitoring device for grounding states of iron core of power transformer
CN113049914B (en) Power transmission line fault diagnosis method and system, electronic equipment and storage medium
Rizvi et al. Real-time ZIP load parameter tracking using adaptive window and variable elimination with realistic synthetic synchrophasor data
CN115186935A (en) Electromechanical device nonlinear fault prediction method and system
CN115115117A (en) Intelligent processing and analyzing system based on block chain
CN111224468B (en) Photovoltaic equipment safe operation and maintenance platform based on cloud computing
CN210428558U (en) Intelligent auxiliary system for power optical cable inspection line

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