CN117409816A - Equipment fault detection method and system based on sound signals - Google Patents
Equipment fault detection method and system based on sound signals Download PDFInfo
- Publication number
- CN117409816A CN117409816A CN202311713611.6A CN202311713611A CN117409816A CN 117409816 A CN117409816 A CN 117409816A CN 202311713611 A CN202311713611 A CN 202311713611A CN 117409816 A CN117409816 A CN 117409816A
- Authority
- CN
- China
- Prior art keywords
- fault
- sound
- wave characteristic
- sound wave
- equipment
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to the technical field of fault detection, and discloses a device fault detection method and system based on sound signals, wherein the method comprises the following steps: collecting equipment sound information in real time, and inputting the sound information into a pre-established fault detection model; outputting whether the currently acquired equipment sound information has fault characteristics or not according to the fault detection model; when the fault characteristics are provided, the fault characteristics are divided into a plurality of sound characteristic sections, and the sound characteristic sections are compared with the fault sound characteristic sets to obtain at least one fault type corresponding to the equipment sound information. According to the invention, the fault judgment is carried out by monitoring the sound information of the equipment in operation in real time, a fault detection model is established in advance, the equipment sound information acquired in real time is input into the fault detection model for carrying out the fault judgment, the equipment sound information which is output as the fault through the fault detection model is subjected to the sectional detailed detection, and then the current fault type of the equipment is obtained, so that the equipment with different faults can be maintained in a targeted manner.
Description
Technical Field
The invention relates to the technical field of fault detection, in particular to a device fault detection method and system based on sound signals.
Background
At present, the power equipment is a very important energy transmission and conversion device, the quantity is very huge, tens of millions of equipment are expected in China, and millions of equipment need to be updated and maintained every year, and the safe, reliable and stable operation of the equipment is the fundamental of the safe, reliable and stable operation of a power supply network, so that the accurate assessment of the operation state of the equipment is realized, the operation stability of the power equipment is effectively maintained, and the maintenance level is improved. Since the mechanical vibration produces sound and has certain regularity when the electric power equipment works, a method for judging the running state of the electric power equipment according to the voiceprint of the electric power equipment is provided. Along with the rapid development of national economy in China in recent years, higher requirements are put forward on the quality and quantity of power supply and distribution networks. The traditional equipment failure method is to combine manual data sampling and online parameter sampling, and maintenance personnel judge the running state of the equipment according to the sampled data. However, since the manual judgment is generally only combined with the sampling data at the current moment, predictability is lacking, faults cannot be effectively predicted, and immeasurable losses can be caused.
Disclosure of Invention
Aiming at the defects, the embodiment of the invention discloses a device fault detection method and a system based on sound signals, which can automatically detect the working operation of the device by collecting the sound signals of the device in real time.
The first aspect of the embodiment of the invention discloses a device fault detection method based on sound signals, which comprises the following steps:
collecting equipment sound information in real time, and inputting the sound information into a pre-established fault detection model;
outputting whether the currently collected equipment sound information has fault characteristics or not according to the fault detection model:
when the fault characteristics are provided, processing the equipment sound information, acquiring the length of the equipment sound information, and filtering noise signals in the equipment sound information; extracting continuous sound wave characteristics from the filtered equipment sound information, dividing the sound wave characteristics into a plurality of sound wave characteristic sections according to preset sectional lengths, and comparing each sound characteristic section with a fault sound characteristic set to obtain at least one fault type corresponding to the equipment sound information.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the method further includes:
and when the fault characteristics are not provided, inputting the equipment sound information into an early warning detection model to output early warning information, wherein the early warning information comprises early warning behaviors and fault early warning types.
In an optional implementation manner, in the first aspect of the embodiment of the present invention, the dividing the acoustic wave feature into a plurality of acoustic wave feature segments according to a preset segment length includes:
calculating the maximum sound wave characteristic length which can be contained by each sound wave characteristic section to be divided based on the preset segmentation length;
calculating the minimum number of sound wave characteristic sections according to the maximum sound wave characteristic length and the total length of sound wave characteristics, and obtaining the sound wave characteristic length contained in the last sound wave characteristic section;
and when the length of the last acoustic wave characteristic section is higher than a preset value, dividing the acoustic wave characteristic section into the acoustic wave characteristic section with the minimum number of acoustic wave characteristic sections.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the comparing each segment of sound feature segment with the fault sound set includes,
comparing each acoustic wave characteristic segment with a pre-stored comparison standard to judge whether the current acoustic wave characteristic segment has fault characteristics or not;
and when the fault characteristics exist, matching the sound wave characteristic section with a fault sound set to obtain the fault type.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the matching the acoustic wave characteristic segment with the fault sound set to obtain a fault type includes:
drawing a corresponding time domain waveform diagram of the sound wave characteristic section, and matching the time domain waveform diagram with fault sound set information;
and calculating the similarity between the time domain waveform diagram and each subset in the fault sound set, and recording the fault type corresponding to the subset with the highest similarity as the fault type of the sound wave characteristic section.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, a manner of establishing the fault detection model includes:
acquiring a plurality of groups of historical fault sound signals, and screening a plurality of groups of fault sounds from the historical fault sound signals;
randomly selecting one half of the multiple groups of fault sounds as input data to train a fault detection model, and correcting the fault detection model by taking the other half of the fault sounds as correction data;
and checking the output result of the fault detection model at intervals of preset time, and when the error rate of the output result is greater than a threshold value, acquiring equipment fault sound information within a set time interval from the current time stamp to perform self-training on the fault detection model.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the screening multiple sets of fault sounds from the historical fault sound signal includes:
extracting a plurality of signal features from each set of historical fault sound signals;
judging whether each signal characteristic in each set of historical fault sound signals exists in other sets of historical fault sound signals;
and extracting sound clips corresponding to signal characteristics existing in other groups of historical fault sound signals.
A second aspect of the embodiment of the present invention discloses an apparatus failure detection system based on a sound signal, including:
the sound collection module is used for: the method comprises the steps of acquiring equipment sound information in real time, and inputting the sound information into a pre-established fault detection model;
and a fault detection module: and the device sound information processing module is used for outputting whether the currently acquired device sound information has fault characteristics according to the fault detection model:
a type determining module: when the fault feature is provided, the device sound information is processed, the length of the device sound information is obtained, and noise signals in the device sound information are filtered; extracting continuous sound wave characteristics from the filtered equipment sound information, dividing the sound wave characteristics into a plurality of sound wave characteristic sections according to preset sectional lengths, and comparing each sound characteristic section with a fault sound characteristic set to obtain at least one fault type corresponding to the equipment sound information.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, the method further includes:
and when the fault characteristics are not provided, inputting the equipment sound information into an early warning detection model to output early warning information, wherein the early warning information comprises early warning behaviors and fault early warning types.
In a second aspect of the embodiment of the present invention, the dividing the acoustic wave feature into a plurality of acoustic wave feature segments according to a preset segment length includes:
calculating the maximum sound wave characteristic length which can be contained by each sound wave characteristic section to be divided based on the preset segmentation length;
calculating the minimum number of sound wave characteristic sections according to the maximum sound wave characteristic length and the total length of sound wave characteristics, and obtaining the sound wave characteristic length contained in the last sound wave characteristic section;
and when the length of the last acoustic wave characteristic section is higher than a preset value, dividing the acoustic wave characteristic section into the acoustic wave characteristic section with the minimum number of acoustic wave characteristic sections.
In a second aspect of the present embodiment, the comparing each segment of sound characteristic with the fault sound set includes,
comparing each acoustic wave characteristic segment with a pre-stored comparison standard to judge whether the current acoustic wave characteristic segment has fault characteristics or not;
and when the fault characteristics exist, matching the sound wave characteristic section with a fault sound set to obtain the fault type.
In a second aspect of the embodiment of the present invention, the matching the acoustic wave characteristic segment with the fault sound set to obtain a fault type includes:
drawing a corresponding time domain waveform diagram of the sound wave characteristic section, and matching the time domain waveform diagram with fault sound set information;
and calculating the similarity between the time domain waveform diagram and each subset in the fault sound set, and recording the fault type corresponding to the subset with the highest similarity as the fault type of the sound wave characteristic section.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, a manner of establishing the fault detection model includes:
acquiring a plurality of groups of historical fault sound signals, and screening a plurality of groups of fault sounds from the historical fault sound signals;
randomly selecting one half of the multiple groups of fault sounds as input data to train a fault detection model, and correcting the fault detection model by taking the other half of the fault sounds as correction data;
and checking the output result of the fault detection model at intervals of preset time, and when the error rate of the output result is greater than a threshold value, acquiring equipment fault sound information within a set time interval from the current time stamp to perform self-training on the fault detection model.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, the step of screening multiple sets of fault sounds from the historical fault sound signals includes:
extracting a plurality of signal features from each set of historical fault sound signals;
judging whether each signal characteristic in each set of historical fault sound signals exists in other sets of historical fault sound signals;
and extracting sound clips corresponding to signal characteristics existing in other groups of historical fault sound signals.
A third aspect of an embodiment of the present invention discloses an electronic device, including: a memory storing executable program code; a processor coupled to the memory; the processor invokes the executable program code stored in the memory to perform the method for detecting equipment failure based on the sound signal disclosed in the first aspect of the embodiment of the present invention.
A fourth aspect of the embodiments of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the method for detecting a device failure based on a sound signal disclosed in the first aspect of the embodiments of the present invention.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
in the embodiment of the invention, the running condition of the equipment is monitored in real time, the fault judgment is carried out by monitoring the sound information of the equipment in running, the fault detection model is established in advance, the equipment sound information acquired in real time is input into the fault detection model for carrying out the fault judgment, the equipment sound information which is output as the fault through the fault detection model is detected in a sectionalized manner in detail, the current fault type of the equipment is further obtained, and further, the subsequent maintenance of the equipment with different faults can be carried out in a targeted manner.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an equipment fault detection method based on a sound signal according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of establishing a fault detection model according to an embodiment of the present invention.
FIG. 3 is a flow chart of another method for detecting equipment failure based on sound signals according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an equipment fault detection system based on an acoustic signal according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present invention are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
The embodiment of the invention discloses a device fault detection method, a device, electronic equipment and a storage medium based on sound signals, wherein in the embodiment, the running condition of the device is monitored in real time, the sound information of the device in running is monitored to carry out fault judgment, a fault detection model is built in advance, the device sound information acquired in real time is input into the fault detection model to carry out fault judgment, the device sound information which is output as faults through the fault detection model is subjected to sectional detailed detection, the current fault type of the device is obtained, and further, the subsequent maintenance of the devices with different faults can be carried out in a targeted mode.
Example 1
Referring to fig. 1, fig. 1 is a flow chart of an apparatus fault detection method based on a sound signal according to an embodiment of the present invention. The execution main body of the method described in the embodiment of the invention is an execution main body composed of software or/and hardware, and the execution main body can receive related information in a wired or/and wireless mode and can send a certain instruction. Of course, it may also have certain processing and storage functions. The execution body may control a plurality of devices, such as a remote physical server or cloud server and related software, or may be a local host or server and related software that performs related operations on a device that is located somewhere, etc. In some scenarios, multiple storage devices may also be controlled, which may be located in the same location or in different locations than the devices. As shown in fig. 1, the method for detecting equipment failure based on sound signals comprises the following steps:
101. and collecting equipment sound information in real time, and inputting the sound information into a pre-established fault detection model.
An electric power device is a stationary electric device, and is a device for converting an ac voltage (current) of a certain value into another voltage (current) of the same frequency or different values. Stationary devices having two or more windings convert the alternating voltage and current of one system to the voltage and current of another system by electromagnetic induction at the same frequency for the transfer of electrical energy, typically with different values of these currents and voltages.
When the equipment fails, the sound information generated during operation is different from that generated during normal operation, so that whether the equipment fails or not can be detected by monitoring the working information of the equipment during operation in real time.
In this step, the manner of establishing the fault detection model is as shown in fig. 2, and includes:
1011. and acquiring a plurality of groups of historical fault sound signals, and screening a plurality of groups of fault sounds from the historical fault sound signals.
The embodiment needs a sufficient number of samples as input data to construct a fault detection model, and multiple groups of historical fault sound signals are selected. The historical fault sound signal is a sound signal collected when the past equipment fails and corresponds to the type of fault, the cause of the fault, the fault maintenance mode and the like which are detected by the sound signal.
Specifically, each set of historical fault sound signals may contain other sound information besides the sound information generated by the faults, and sound fragments containing fault characteristics are screened from the historical fault sound signals to be used as samples, so that the situation that the whole set of historical fault sound signals are used as samples to cause too much redundancy of data quantity and further reduce the data running speed and the like can be avoided.
In an embodiment, screening a plurality of groups of fault sounds from the historical fault sound signals includes: extracting a plurality of signal features from each set of historical fault sound signals; judging whether each signal characteristic in each set of historical fault sound signals exists in other sets of historical fault sound signals; and extracting sound clips corresponding to signal characteristics existing in other groups of historical fault sound signals.
When the signature is also present in other sets of historical fault sound signals, it is most likely that the sound is generated when the fault occurs. And because there may be two or more fault types in a set of historical fault sound signals, and more than two fault types are more likely to exist in a plurality of sets of historical fault sound information, signal features in each set of historical fault sound signals are extracted respectively, and more comprehensive fault features can be extracted, so that a more perfect fault detection model is built.
1012. And randomly selecting one half of the multiple groups of fault sounds as input data to train a fault detection model, and correcting the fault detection model by using the other half of the fault sounds as correction data.
The embodiment groups the selected fault sounds, wherein a part of the fault sounds are used as training sample data, and a part of the fault sounds are used as correction model sample data, so that the established model is further corrected and corrected, and the output result is more accurate.
1013. And checking the output result of the fault detection model at intervals of preset time, and when the error rate of the output result is greater than a threshold value, acquiring equipment fault sound information within a set time interval from the current time stamp to perform self-training on the fault detection model.
Embodiments provide for the verification accuracy of the fault detection model by modeling and correcting the fault detection model through historical data and verifying and self-training the fault detection model at intervals.
102. And outputting whether the currently collected equipment sound information has fault characteristics or not according to the fault detection model.
103. When the fault characteristics are provided, processing the equipment sound information, acquiring the length of the equipment sound information, and filtering noise signals in the equipment sound information; extracting continuous sound wave characteristics from the filtered equipment sound information, dividing the sound wave characteristics into a plurality of sound wave characteristic sections according to preset sectional lengths, and comparing each sound characteristic section with a fault sound characteristic set to obtain at least one fault type corresponding to the equipment sound information.
Fig. 3 is a schematic flow chart of another method for detecting equipment failure based on an acoustic signal according to this embodiment, as shown in fig. 3, the method for detecting equipment failure includes:
301. and collecting equipment sound information in real time, and inputting the sound information into a pre-established fault detection model.
302. And outputting whether the currently collected equipment sound information has fault characteristics or not according to the fault detection model.
303. When the fault characteristics are provided, processing the equipment sound information, acquiring the length of the equipment sound information, and filtering noise signals in the equipment sound information; extracting continuous sound wave characteristics from the filtered equipment sound information, dividing the sound wave characteristics into a plurality of sound wave characteristic sections according to preset sectional lengths, and comparing each sound characteristic section with a fault sound characteristic set to obtain at least one fault type corresponding to the equipment sound information.
In this step, the acoustic wave feature is divided into a plurality of acoustic wave feature segments according to a preset segment length, including: calculating the maximum sound wave characteristic length which can be contained by each sound wave characteristic section to be divided based on the preset segmentation length; calculating the minimum number of sound wave characteristic sections according to the maximum sound wave characteristic length and the total length of sound wave characteristics, and obtaining the sound wave characteristic length contained in the last sound wave characteristic section; and when the length of the last acoustic wave characteristic section is higher than a preset value, dividing the acoustic wave characteristic section into the acoustic wave characteristic section with the minimum number of acoustic wave characteristic sections.
In the embodiment, according to the preset maximum length which can be contained by each section of sound wave characteristic degree, calculating how many sections of the sound information to be divided at the present time can be divided at most. The preset segmentation length refers to the length of each sound wave characteristic segment after division, and the number of sound wave characteristics which can be included in the longest sound wave characteristic segment of each segment can be calculated after division. It should be noted that the preset segment length may be a specific value or a data range. For example, the preset segment length may be 5 units, or may be set to 2-5 units. The sound wave characteristic is 24 units, and can be divided into 5 sound wave characteristic sections after being divided into 5 units, but the four sound wave characteristic sections all comprise 5 units, the last sound wave characteristic section comprises 4 units, the maximum sound wave characteristic length is obtained at this time to be 5, and the minimum number of sound wave characteristic sections is 5 (the minimum sound wave characteristic section can be divided into 5 sound wave characteristic sections). And assuming that the preset segment length is between 2 and 5, in this case, under the condition that the acoustic wave characteristics are 24 units, the acoustic wave can be divided into 12 acoustic wave characteristic segments after being divided according to 2 units, and the length of each acoustic wave characteristic segment is 2, so that the division at this time is not the maximum acoustic wave characteristic length defined by the embodiment. In the embodiment, the minimum number of acoustic wave feature segments is calculated according to the maximum acoustic wave feature length and the total length of the acoustic wave features, and the acoustic wave feature length contained in the acoustic wave feature segment of the last segment is obtained, and also taking the previous example as an example, the acoustic wave feature is 24 units, the preset segment length is 5 units, the minimum number of acoustic wave feature segments is 5, at this time, the acoustic wave feature length contained in the acoustic wave feature segment of the last segment is 4 units, and assuming that the preset value is 5, that is, lower than the preset value, at this time, the 24 acoustic wave feature segments are divided into 5+1=6 acoustic wave feature segments, then, in another example, the acoustic wave feature segments each contain 4 units, and assuming that the preset value is 3, that is, higher than the preset value, at this time, the 24 acoustic wave feature segments are divided into 5 acoustic wave feature segments. The embodiment adopts the dividing mode, so that the number of sound wave characteristics contained in each sound wave characteristic section can be better made to be more average.
Comparing each sound characteristic segment with a fault sound set, including comparing each sound characteristic segment with a pre-stored comparison standard to judge whether the current sound characteristic segment has fault characteristics; and when the fault characteristics exist, matching the sound wave characteristic section with a fault sound set to obtain the fault type.
Further embodiments match the acoustic signature with a fault sound set to obtain a fault type, comprising: drawing a corresponding time domain waveform diagram of the sound wave characteristic section, and matching the time domain waveform diagram with fault sound set information; and calculating the similarity between the time domain waveform diagram and each subset in the fault sound set, and recording the fault type corresponding to the subset with the highest similarity as the fault type of the sound wave characteristic section. The example processing can adopt the image comparison method of the time domain waveform diagram, can also directly adopt sound for comparison, and calculates the similarity. The embodiment calculates the similarity by respectively comparing each section of sound wave characteristic section, so that the sound signals possibly collected in the whole way can correspond to various fault types, and the embodiment adopts a mode of dividing the sound wave characteristic sections first, firstly, the data capacity of each comparison can be reduced, the comparison can be completed more quickly, meanwhile, the sound wave characteristic sections where faults occur can be found more accurately, and the fault types corresponding to different sound wave characteristic sections can be analyzed.
304. And when the fault characteristics are not provided, inputting the equipment sound information into an early warning detection model to output early warning information, wherein the early warning information comprises early warning behaviors and fault early warning types.
In the embodiment, after the collected sound signal is detected by the fault detection model, the sound signal is judged to have no fault characteristics, fault early warning detection is further carried out, the sound signal is input into the pre-established early warning detection model, and whether the sound signal meets the early warning standard is judged. The early warning behavior of the embodiment includes sending out an early warning signal or not, and may further include early warning measures, that is, for example, when a fault risk is detected, corresponding intervention measures are generated and sent to the user.
Example two
Referring to fig. 4, fig. 4 is a schematic structural diagram of an apparatus for detecting a fault of a device based on an acoustic signal according to an embodiment of the present invention. As shown in fig. 4, the apparatus for detecting a malfunction of a device based on a sound signal may include: sound collection module 401, fault detection module 402, type determination module 403, wherein sound collection module 401: the method comprises the steps of acquiring equipment sound information in real time, and inputting the sound information into a pre-established fault detection model; fault detection module 402: and the device sound information processing module is used for outputting whether the currently acquired device sound information has fault characteristics according to the fault detection model: type determination module 403: when the fault feature is provided, the device sound information is processed, the length of the device sound information is obtained, and noise signals in the device sound information are filtered; extracting continuous sound wave characteristics from the filtered equipment sound information, dividing the sound wave characteristics into a plurality of sound wave characteristic sections according to preset sectional lengths, and comparing each sound characteristic section with a fault sound characteristic set to obtain at least one fault type corresponding to the equipment sound information.
In an embodiment, the system may further include an early warning module: and the device sound information is used for inputting the device sound information into the early warning detection model to output early warning information when the device sound information does not have the fault characteristics, and the early warning information comprises early warning behaviors and fault early warning types.
In the embodiment of the type determining module 403, the dividing the acoustic wave feature into a plurality of acoustic wave feature segments according to a preset segment length includes: calculating the maximum sound wave characteristic length which can be contained by each sound wave characteristic section to be divided based on the preset segmentation length; calculating the minimum number of sound wave characteristic sections according to the maximum sound wave characteristic length and the total length of sound wave characteristics, and obtaining the sound wave characteristic length contained in the last sound wave characteristic section; and when the length of the last acoustic wave characteristic section is higher than a preset value, dividing the acoustic wave characteristic section into the acoustic wave characteristic section with the minimum number of acoustic wave characteristic sections.
The comparing each sound characteristic segment with the fault sound set specifically includes comparing each sound characteristic segment with a pre-stored comparison standard to determine whether the current sound characteristic segment has a fault characteristic; and when the fault characteristics exist, matching the sound wave characteristic section with a fault sound set to obtain the fault type.
Further, matching the acoustic wave characteristic segment with the fault sound set to obtain a fault type, including: drawing a corresponding time domain waveform diagram of the sound wave characteristic section, and matching the time domain waveform diagram with fault sound set information; and calculating the similarity between the time domain waveform diagram and each subset in the fault sound set, and recording the fault type corresponding to the subset with the highest similarity as the fault type of the sound wave characteristic section.
In the sound collection module 401 of the embodiment, the manner of establishing the fault detection model includes: acquiring a plurality of groups of historical fault sound signals, and screening a plurality of groups of fault sounds from the historical fault sound signals; randomly selecting one half of the multiple groups of fault sounds as input data to train a fault detection model, and correcting the fault detection model by taking the other half of the fault sounds as correction data; and checking the output result of the fault detection model at intervals of preset time, and when the error rate of the output result is greater than a threshold value, acquiring equipment fault sound information within a set time interval from the current time stamp to perform self-training on the fault detection model.
In the above, the step of screening a plurality of groups of fault sounds from the historical fault sound signals includes: extracting a plurality of signal features from each set of historical fault sound signals; judging whether each signal characteristic in each set of historical fault sound signals exists in other sets of historical fault sound signals; and extracting sound clips corresponding to signal characteristics existing in other groups of historical fault sound signals.
Example III
Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the invention. The electronic device may be a computer, a server, or the like, and of course, may also be an intelligent device such as a mobile phone, a tablet computer, a monitor terminal, or the like, and an image acquisition device having a processing function. As shown in fig. 5, the electronic device may include:
a memory 501 in which executable program codes are stored;
a processor 502 coupled to the memory 501;
the processor 502 invokes executable program codes stored in the memory 501 to perform some or all of the steps in the sound signal-based device failure detection method in the first embodiment.
An embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute part or all of the steps in the sound signal-based device failure detection method in the first embodiment.
The embodiment of the invention also discloses a computer program product, wherein when the computer program product runs on a computer, the computer is caused to execute part or all of the steps in the equipment fault detection method based on the sound signal in the first embodiment.
The embodiment of the invention also discloses an application release platform, wherein the application release platform is used for releasing a computer program product, and the computer program product enables the computer to execute part or all of the steps in the equipment fault detection method based on the sound signal in the first embodiment when running on the computer.
In various embodiments of the present invention, it should be understood that the size of the sequence numbers of the processes does not mean that the execution sequence of the processes is necessarily sequential, and the execution sequence of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, or a part contributing to the prior art or all or part of the technical solution, may be embodied in the form of a software product stored in a memory, comprising several requests for a computer device (which may be a personal computer, a server or a network device, etc., in particular may be a processor in a computer device) to execute some or all of the steps of the method according to the embodiments of the present invention.
In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a, from which B can be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information.
Those of ordinary skill in the art will appreciate that some or all of the steps of the various methods of the described embodiments may be implemented by hardware associated with a program that may be stored in a computer-readable storage medium, including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM), or other optical disk Memory, magnetic disk Memory, tape Memory, or any other medium capable of being used to carry or store data that is readable by a computer.
The method, system, electronic device and storage medium for detecting equipment failure based on sound signals disclosed in the embodiments of the present invention are described in detail, and specific examples are applied to illustrate the principles and embodiments of the present invention, and the description of the above embodiments is only used to help understand the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (9)
1. A method for detecting a device failure based on an acoustic signal, comprising:
collecting equipment sound information in real time, and inputting the sound information into a pre-established fault detection model;
outputting whether the currently acquired equipment sound information has fault characteristics or not according to the fault detection model;
when the fault characteristics are provided, processing the equipment sound information, acquiring the length of the equipment sound information, and filtering noise signals in the equipment sound information; extracting continuous sound wave characteristics from the filtered equipment sound information, and calculating the maximum sound wave characteristic length which can be contained in each sound wave characteristic section to be divided based on the preset segmentation length; calculating the minimum number of sound wave characteristic sections according to the maximum sound wave characteristic length and the total length of sound wave characteristics, and obtaining the sound wave characteristic length contained in the last sound wave characteristic section; when the length of the last sound wave characteristic section is lower than a preset value, dividing the sound wave characteristic section into the sound wave characteristic section minimum number+1 sections, when the length of the last sound wave characteristic section is higher than the preset value, dividing the sound wave characteristic section into the sound wave characteristic section minimum number sections, and comparing each sound characteristic section with a fault sound characteristic set to obtain at least one fault type corresponding to the equipment sound information.
2. The apparatus failure detection method according to claim 1, characterized by further comprising:
and when the fault characteristics are not provided, inputting the equipment sound information into an early warning detection model to output early warning information, wherein the early warning information comprises early warning behaviors and fault early warning types.
3. The apparatus fault detection method of claim 1, wherein said comparing each segment of sound signature to the fault sound set comprises,
comparing each acoustic wave characteristic segment with a pre-stored comparison standard to judge whether the current acoustic wave characteristic segment has fault characteristics or not;
and when the fault characteristics exist, matching the sound wave characteristic section with a fault sound set to obtain the fault type.
4. A method for detecting a fault in a device according to claim 3, wherein said matching the acoustic signature with the fault sound set to obtain a fault type comprises:
drawing a corresponding time domain waveform diagram of the sound wave characteristic section, and matching the time domain waveform diagram with fault sound set information;
and calculating the similarity between the time domain waveform diagram and each subset in the fault sound set, and recording the fault type corresponding to the subset with the highest similarity as the fault type of the sound wave characteristic section.
5. The apparatus fault detection method of claim 1, wherein the means for establishing the fault detection model comprises:
acquiring a plurality of groups of historical fault sound signals, and screening a plurality of groups of fault sounds from the historical fault sound signals;
randomly selecting one half of the multiple groups of fault sounds as input data to train a fault detection model, and correcting the fault detection model by taking the other half of the fault sounds as correction data;
and checking the output result of the fault detection model at intervals of preset time, and when the error rate of the output result is greater than a threshold value, acquiring equipment fault sound information within a set time interval from the current time stamp to perform self-training on the fault detection model.
6. The apparatus fault detection method of claim 5, wherein screening a plurality of sets of fault sounds from the historical fault sound signal comprises:
extracting a plurality of signal features from each set of historical fault sound signals;
judging whether each signal characteristic in each set of historical fault sound signals exists in other sets of historical fault sound signals;
and extracting sound clips corresponding to signal characteristics existing in other groups of historical fault sound signals.
7. An acoustic signal based equipment failure detection system, comprising:
the sound collection module is used for: the method comprises the steps of acquiring equipment sound information in real time, and inputting the sound information into a pre-established fault detection model;
and a fault detection module: and the device sound information processing module is used for outputting whether the currently acquired device sound information has fault characteristics according to the fault detection model:
a type determining module: when the fault feature is provided, the device sound information is processed, the length of the device sound information is obtained, and noise signals in the device sound information are filtered; extracting continuous sound wave characteristics from the filtered equipment sound information, and calculating the maximum sound wave characteristic length which can be contained in each sound wave characteristic section to be divided based on the preset segmentation length; calculating the minimum number of sound wave characteristic sections according to the maximum sound wave characteristic length and the total length of sound wave characteristics, and obtaining the sound wave characteristic length contained in the last sound wave characteristic section; when the length of the last sound wave characteristic section is lower than a preset value, dividing the sound wave characteristic section into the sound wave characteristic section minimum number+1 sections, when the length of the last sound wave characteristic section is higher than the preset value, dividing the sound wave characteristic section into the sound wave characteristic section minimum number sections, and comparing each sound characteristic section with a fault sound characteristic set to obtain at least one fault type corresponding to the equipment sound information.
8. An electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor invokes the executable program code stored in the memory for performing the sound signal based device fault detection method of any one of claims 1 to 6.
9. A computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the sound signal-based device failure detection method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311713611.6A CN117409816B (en) | 2023-12-14 | 2023-12-14 | Equipment fault detection method and system based on sound signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311713611.6A CN117409816B (en) | 2023-12-14 | 2023-12-14 | Equipment fault detection method and system based on sound signals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117409816A true CN117409816A (en) | 2024-01-16 |
| CN117409816B CN117409816B (en) | 2024-03-26 |
Family
ID=89500279
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311713611.6A Active CN117409816B (en) | 2023-12-14 | 2023-12-14 | Equipment fault detection method and system based on sound signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117409816B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118293710A (en) * | 2024-03-29 | 2024-07-05 | 建龙西林钢铁有限公司 | Belt type roasting production line equipment fault detection method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012046602A1 (en) * | 2010-10-05 | 2012-04-12 | 国立大学法人 九州工業大学 | Fault detection system, extraction device, fault detection method, program, and recording medium |
| US20120143610A1 (en) * | 2010-12-03 | 2012-06-07 | Industrial Technology Research Institute | Sound Event Detecting Module and Method Thereof |
| WO2016027996A1 (en) * | 2014-08-21 | 2016-02-25 | 호원대학교산학협력단 | Power equipment sound diagnosis system |
| CN113657221A (en) * | 2021-08-04 | 2021-11-16 | 浙江浙能台州第二发电有限责任公司 | Power plant equipment state monitoring method based on intelligent sensing technology |
| CN114639391A (en) * | 2020-12-24 | 2022-06-17 | 亚信科技（中国）有限公司 | Mechanical failure prompting method and device, electronic equipment and storage medium |
| WO2023279382A1 (en) * | 2021-07-09 | 2023-01-12 | 徐萌萌 | Motor bearing running state fault detection method and system |
| CN116092519A (en) * | 2021-11-03 | 2023-05-09 | 株式会社日立制作所 | Vehicle fault detection method and system |
| CN116665710A (en) * | 2023-07-26 | 2023-08-29 | 中国南方电网有限责任公司超高压输电公司广州局 | Fault identification method and device for gas-insulated switchgear and computer equipment |
-
2023
- 2023-12-14 CN CN202311713611.6A patent/CN117409816B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012046602A1 (en) * | 2010-10-05 | 2012-04-12 | 国立大学法人 九州工業大学 | Fault detection system, extraction device, fault detection method, program, and recording medium |
| US20120143610A1 (en) * | 2010-12-03 | 2012-06-07 | Industrial Technology Research Institute | Sound Event Detecting Module and Method Thereof |
| WO2016027996A1 (en) * | 2014-08-21 | 2016-02-25 | 호원대학교산학협력단 | Power equipment sound diagnosis system |
| CN114639391A (en) * | 2020-12-24 | 2022-06-17 | 亚信科技（中国）有限公司 | Mechanical failure prompting method and device, electronic equipment and storage medium |
| WO2023279382A1 (en) * | 2021-07-09 | 2023-01-12 | 徐萌萌 | Motor bearing running state fault detection method and system |
| CN113657221A (en) * | 2021-08-04 | 2021-11-16 | 浙江浙能台州第二发电有限责任公司 | Power plant equipment state monitoring method based on intelligent sensing technology |
| CN116092519A (en) * | 2021-11-03 | 2023-05-09 | 株式会社日立制作所 | Vehicle fault detection method and system |
| CN116665710A (en) * | 2023-07-26 | 2023-08-29 | 中国南方电网有限责任公司超高压输电公司广州局 | Fault identification method and device for gas-insulated switchgear and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 曹文明;王耀南;: "基于音频识别的无人值守变电站设备在线监测", 湖南大学学报(自然科学版), vol. 40, no. 09, 30 September 2013 (2013-09-30), pages 48 - 55 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118293710A (en) * | 2024-03-29 | 2024-07-05 | 建龙西林钢铁有限公司 | Belt type roasting production line equipment fault detection method and device |
| CN118293710B (en) * | 2024-03-29 | 2025-03-21 | 建龙西林钢铁有限公司 | A belt roasting production line equipment fault detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117409816B (en) | 2024-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11905926B2 (en) | Method and apparatus for inspecting wind turbine blade, and device and storage medium thereof | |
| CN110688617B (en) | Fan vibration abnormity detection method and device | |
| CN114325256A (en) | Power equipment partial discharge identification method, system, equipment and storage medium | |
| CN117409816B (en) | Equipment fault detection method and system based on sound signals | |
| CN114184870A (en) | Non-invasive load identification method and device | |
| CN111046942A (en) | Turnout fault judgment method and device | |
| CN117783792A (en) | Valve side casing insulation status detection method and system based on multi-parameter real-time monitoring | |
| CN108009063A (en) | The method of a kind of electronic equipment fault threshold detection | |
| CN116739829B (en) | Big data-based power data analysis method, system and medium | |
| CN115936658A (en) | A method, system, and readable storage medium for abnormal detection of power equipment | |
| CN113655344B (en) | Power distribution network fault identification method, device, terminal and medium | |
| CN120429751A (en) | A charging pile fault identification method, device and medium based on power fingerprint | |
| CN119829995A (en) | Method and device for rapidly extracting ultrahigh frequency partial discharge characteristic signals of hydraulic generator | |
| CN112084673A (en) | Automatic setting method and device for switch friction current | |
| CN116087660B (en) | Arc fault detection method and arc fault detection model training method | |
| CN115798511A (en) | Method for detecting abnormality of industrial equipment through sound | |
| CN114325215A (en) | Intensive detection system for power equipment state and application method thereof | |
| CN113607992B (en) | A detection wave generation method and related devices for a DC power distribution protection device | |
| CN118643448B (en) | Three-phase transformer winding fault positioning method, device and equipment | |
| CN119209932B (en) | A power distribution system power monitoring cloud platform based on transformer | |
| CN121253897A (en) | A method and system for monitoring residual current in a station AC system | |
| CN119598372A (en) | Equipment start-stop state classification model training method, equipment start-stop state classification method, electronic equipment and storage medium | |
| CN117827594A (en) | Log abnormality detection method and device, electronic equipment and storage medium | |
| CN119362366A (en) | Safety protection method and system for intelligent high-voltage circuit breaker control system device | |
| CN119150008A (en) | Separation method and device of equipment signals, computer program product and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |