CN115238121A - Rotating machine health and fault feature identification method based on audio technology - Google Patents
Rotating machine health and fault feature identification method based on audio technology Download PDFInfo
- Publication number
- CN115238121A CN115238121A CN202210828173.7A CN202210828173A CN115238121A CN 115238121 A CN115238121 A CN 115238121A CN 202210828173 A CN202210828173 A CN 202210828173A CN 115238121 A CN115238121 A CN 115238121A
- Authority
- CN
- China
- Prior art keywords
- audio
- data
- fault
- voiceprint
- health
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/632—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/638—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G10L25/48—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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a method for identifying health and fault characteristics of a rotating machine based on an audio technology, which relates to the field of equipment operation detection and comprises the following steps of S1: collecting voiceprint information of a rotating machine in the field to establish a database; s2: constructing a training characteristic neural network model, establishing a data processing platform, and comprehensively planning remote signaling, remote measurement, remote sensing data and acoustic time sequence data; s3: deploying a plurality of audio collectors on the spot to collect data; s4: importing data into a characteristic neural network model; s5: feature recognition and abnormal warning; s6: and (4) archiving abnormal data and correcting a database. The method comprises the steps of leading audio information into a characteristic neural network model, identifying health and fault characteristics, detecting the running condition of a rotating machine, collecting abnormal warning to correct a database, calculating and judging mass data in real time, reducing detection response time after a fault occurs, automatically monitoring and collecting, automatically analyzing the running state and automatically early warning, and enabling a worker not to enter a dangerous space in the whole process.
Description
Technical Field
The invention relates to the field of equipment operation detection, in particular to the field of equipment operation audio detection, and discloses a rotating machinery health and fault feature identification method based on an audio technology.
Background
With the rapid development of science and technology, the industrial mechanization degree is higher and higher, mechanical faults are increased correspondingly, and the damage of the bearing accounts for a large proportion of the mechanical faults. Due to the limitation of working environment and conditions, the checking, judging, maintaining and overhauling of the health condition of the bearing are inconvenient. And the operation is extremely unsafe at the rotating part, and personal injury can be caused by carelessness. The production benefit of enterprises is influenced, the personal safety of workers is also harmed, and the problem to be solved by each enterprise is always urgent.
The traditional examination method is characterized in that whether a bearing is good or bad is judged by ears, hands and experiences of workers, the traditional examination method is inaccurate, inconvenient and dangerous, working conditions of the traditional examination method are complex and severe when a rotating machine is usually in a limited space, and the traditional examination method often contains high temperature and high pressure, chemical pollution, noise pollution, toxic and harmful substances, mechanical damage and the like, so that the health of workers is affected. There are still a lot of non-standardized factory scenarios in the industrial field, which depend on the hearing of workers and are collectively referred to as experience in the industry. The sound is one of the most important comprehensive characteristics of the health condition of the motor equipment, the quality inspection link of the motor product needs the sound of equipment heard by a master in the field, and the quality of the product depends on the experience level of the master in polishing for many years.
On one hand, the manual quality inspection is difficult to form a unified standard through manual detection, the subjective randomness is high, and the risk of false detection and missed detection exists; on the other hand, the defects are difficult to trace and feed back, and the current product process flow cannot be effectively improved.
Disclosure of Invention
The invention aims to: in order to solve the technical problems, the invention provides a rotating machine health and fault feature identification method based on an audio technology.
The invention specifically adopts the following technical scheme for realizing the purpose:
1. a rotating machinery health and fault feature recognition method based on audio technology comprises the following steps;
s1: collecting voiceprint information of the rotating machinery through an audio collector on the spot, establishing a voiceprint database by collecting N groups of voice frequency spectrums within fixed time, wherein the database comprises normal operation voiceprint characteristics and classical fault voiceprint characteristics, and preprocessing data after collection;
s2: constructing a neural network model, establishing a training model, repeatedly carrying out operation training on the training model through a plurality of collected classical sound frequency spectrums to be identified to obtain a characteristic neural network model, optimizing identification parameters, identifying normal operation voiceprint characteristics and classical fault voiceprint characteristics by the characteristic neural network model, establishing a data processing platform, and comprehensively planning remote signaling, remote measurement, remote sensing data and acoustic time sequence data;
s3: deploying a plurality of audio collectors on the spot, adopting corrosion-resistant high-temperature-resistant high-pressure-resistant audio collecting equipment, attaching an infinite communication module on the audio collectors, synchronously collecting on-spot audio information according to time gradient, and preprocessing data after collection;
s4: the computer leads the on-site audio data into a characteristic neural network model, a data processing platform comprehensively and comprehensively plans remote signaling, remote sensing data and acoustic time sequence data to carry out health and fault characteristic identification, and simultaneously the computer displays the acquired frequency spectrum and frequency domain characteristic data on a display screen on the data processing platform in a real-time chart manner;
s5: judging whether the equipment operates normally or not according to the characteristic identification, and giving a warning if the equipment is abnormal, and simultaneously storing an abnormal record;
s6: after each warning, the system automatically records the monitoring data as a sample plate into a database according to whether the warning is mistaken and the severity is graded, and corrects the database again; for more serious accidents which may occur, the alarm can be given under the condition of lower confidence coefficient, the fault recording and displaying are carried out on the data processing platform, meanwhile, the operation information of each piece of equipment is comprehensively processed on the data processing platform, the health degree of the equipment is comprehensively judged, the information is pushed through the internet, associated apps, short messages and telephone channels in real time, the online diagnosis of difficulties is realized through the internet, and the further decision making of a manager is facilitated.
Further, in step S1, the voiceprint feature takes the sound intensity and the sound pressure as main features, the acquisition time is 3S, and the logarithmic transformation based on the time-series signal processing is performed after the acquisition.
Further, in step S1, collecting the voiceprint information of the rotating machine, inevitably doping noise in the process of collecting a normal running voiceprint sample, removing part of the noise by using a depth residual error network ResNet method, namely separating different noises by using different thresholds, noticing unimportant characteristics by an attention mechanism, and setting the noise to zero by using a soft threshold function; important identification features are noticed through an attention mechanism and are reserved, so that the capability of extracting useful features from a noise-containing signal by a deep neural network is enhanced, namely, a contrast frequency spectrum is repeatedly analyzed, noise is removed, and the precision is improved.
Further, in step S2, optimizing the identification parameters includes combining multiple groups of normal operation voiceprint features and classical failure voiceprint features into a test group, comparing and verifying the test group with the normal operation voiceprint features and the classical failure voiceprint sample features in the neural network model, capturing a feature spectrum, obtaining a feature neural network model if the verification is passed by using an automatic parameter searching method, and if the verification is not passed, continuing to construct the neural network model in step S2, and establishing a training model until the precision requirement is met.
Further, in step S3, data is preprocessed after acquiring the solid audio information, and the processing method is the same as that of removing part of the noise by using the depth residual error network ResNet method in step S1.
Furthermore, in the process of removing noise, voice print of a person and common maintenance voice print removal are additionally introduced, and interference of the person and maintenance work voice is eliminated.
Further, in step S3, a plurality of audio collectors synchronously collect audio, collect audio according to the collection time of 3S each time, and perform logarithmic transformation based on time-sequence signal processing after collection.
Further, in step S5, the warning mode is a plurality of reasonable combinations of short message, telephone, light and audio.
Further, in step S1, when the database information in the early stage is insufficient, data expansion is performed by linearly combining the collected data of the plurality of audio collectors and adding noise, so as to increase the data volume.
The invention has the following beneficial effects:
1. according to the method, voiceprint information of corresponding rotating mechanical equipment is collected on the spot, a voiceprint database is processed and established, meanwhile, a characteristic neural network model for identifying the normal operation voiceprint characteristics and the classical fault voiceprint characteristics of the rotating machinery is trained according to the content of the voiceprint database, a plurality of audio collectors are deployed on the spot, the processed audio information is led into the characteristic neural network model through an infinite communication module, health and fault characteristic identification is carried out, the operation condition of the rotating machinery is detected, meanwhile, abnormal alarms are collected to correct the database, unmanned automatic monitoring collection, automatic operation state analysis, automatic early warning, abnormal detection and collection are achieved, one period conversion and data fusion are carried out for three seconds, large quantities of data are calculated and judged in real time, the efficiency of data processing judgment is improved, the time of detection response after faults occur is reduced, the guarantee of safe operation of the equipment is greatly improved, workers do not need to enter a dangerous space in the whole process, meanwhile, the detection standard is more accurate, the detection result is subjected to archive analysis, and unmanned monitoring, automatic early warning is achieved in the whole process;
2. by continuously collecting the warning data, the system automatically records the monitoring data as a sample into a database according to whether the warning data is mistakenly reported and the severity is graded, and corrects the database again; for more serious accidents which may occur, the alarm can be given under the condition of lower confidence coefficient, fault recording and displaying are carried out on the data processing platform at the same time, meanwhile, operation information of each piece of equipment is comprehensively processed on the data processing platform, the health degree of the equipment is comprehensively judged, information pushing is carried out in real time through the internet, associated apps, short messages and telephone channels, and difficult online diagnosis is realized through the internet, so that a manager can make decisions conveniently, the precision of the system is continuously improved, and the operation safety level of the rotating machinery is improved;
3. the computer displays the acquired frequency spectrum and frequency domain characteristic data on a display screen on a data processing platform in a real-time chart manner, so that the method is more visual and convenient.
Drawings
FIG. 1 is a schematic flow diagram of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention, generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
As shown in fig. 1, the present embodiment provides a method for identifying health and fault characteristics of a rotating machine based on an audio technology, which is characterized by comprising the following steps;
s1: collecting voiceprint information of the rotating machinery through an audio collector on the spot, establishing a voiceprint database by collecting N groups of voice frequency spectrums within fixed time, wherein the database comprises normal operation voiceprint characteristics and classical fault voiceprint characteristics, and preprocessing data after collection;
s2: constructing a neural network model, establishing a training model, repeatedly carrying out operation training on the training model through a plurality of collected classical sound frequency spectrums to be identified to obtain a characteristic neural network model, optimizing identification parameters, identifying normal operation voiceprint characteristics and classical fault voiceprint characteristics by the characteristic neural network model, establishing a data processing platform, and comprehensively planning remote signaling, remote measurement, remote sensing data and acoustic time sequence data;
s3: a plurality of audio collectors are deployed on the spot, corrosion-resistant high-temperature-resistant high-pressure-resistant audio collecting equipment is adopted, an infinite communication module is attached to each audio collector, the infinite communication module can be one or more of Bluetooth, wifi and a mobile network, the audio collectors can also adopt wired transmission, on-spot audio information is synchronously collected according to time gradient, and data is preprocessed after the on-spot audio information is collected;
s4: the computer leads the on-site audio data into a characteristic neural network model, a data processing platform comprehensively and comprehensively plans remote signaling, remote sensing data and acoustic time sequence data to carry out health and fault characteristic identification, and simultaneously the computer displays the acquired frequency spectrum and frequency domain characteristic data on a display screen on the data processing platform in a real-time chart manner;
s5: judging whether the equipment operates normally or not according to the characteristic identification, and giving a warning if the equipment is abnormal, and simultaneously storing an abnormal record;
s6: after each warning, the system automatically records the monitoring data as a sample plate into a database according to whether the warning is mistakenly reported and the severity is graded, and corrects the database again; for more serious accidents which may occur, an alarm can be given under the condition of lower confidence coefficient, fault recording and displaying are carried out on the data processing platform, operation information of each device is comprehensively processed on the data processing platform, the health degree of the device is comprehensively judged, information pushing is carried out in real time through the internet, associated apps, short messages and telephone channels, and difficult online diagnosis is realized through the internet, so that a manager can make a decision conveniently.
In step S1, the voiceprint feature takes the sound intensity and the sound pressure as main features, the acquisition time is 3S, and logarithmic transformation based on time-series signal processing is performed after the acquisition.
In the step S1, collecting the voiceprint information of the rotating machinery, inevitably doping noise in the collection process of a normally running voiceprint sample, removing partial noise by a depth residual error network ResNet method, namely adopting different thresholds to separate different noises, paying attention to unimportant characteristics by an attention machine, and setting the characteristics to be zero by a soft threshold function; important identification features are noticed through an attention mechanism and are reserved, so that the capability of extracting useful features from a noise-containing signal by a deep neural network is enhanced, namely, a contrast frequency spectrum is repeatedly analyzed, noise is removed, and the precision is improved.
In the step S2, optimizing the identification parameters comprises combining multiple groups of normal operation voiceprint characteristics and classical failure voiceprint characteristics into a test group, comparing and verifying the test group with the normal operation voiceprint characteristics and the classical failure voiceprint sample characteristics in the neural network model, capturing a characteristic spectrum, obtaining a characteristic neural network model if the verification is passed by adopting an automatic parameter searching method, and continuing to construct the neural network model in the step S2 if the verification is not passed, and constructing a training model until the precision requirement is met.
In the step S3, data are preprocessed after solid audio information is collected, and the processing mode is the same as that of removing partial noise by adopting a deep residual error network ResNet method in the step S1. In the process of removing noise, a voice print of a person is additionally led in, the voice print of the person is removed through common maintenance, and the interference of the voice of the person and the voice of maintenance work is eliminated.
In step S3, a plurality of audio collectors synchronously collect audio, the audio is synchronously collected according to the collection time of 3S each time, and logarithmic transformation based on time sequence signal processing is carried out after collection.
In step S5, the warning mode is a plurality of reasonable combinations of short messages, telephone calls, light and audio.
In the step S1, when the information of the early database is insufficient, the data is expanded by linearly combining the collected data of a plurality of audio collectors and adding noise, so that the data volume is increased.
By continuously collecting the warning data, the system automatically records the monitoring data as a sample into a database according to whether the warning data is mistakenly reported and the severity is graded, and corrects the database again; for more serious accidents which may occur, the alarm can be given under the condition of lower confidence coefficient, the fault recording and displaying are carried out on the data processing platform, meanwhile, the operation information of each piece of equipment is comprehensively processed on the data processing platform, the health degree of the equipment is comprehensively evaluated, the information is pushed through the internet, associated apps, short messages and telephone channels in real time, and the online diagnosis of difficulties is realized through the internet, so that a manager can make decisions conveniently, the precision of the system is continuously improved, and the operation safety level of the rotating machinery is improved.
Example 2
The embodiment 2 and the embodiment 1 are characterized in that a comparison method is adopted, a frequency spectrum of a general rotating machine is regular and relatively stable regardless of a fault or normal operation state, other noises are relatively disordered, and other noises can be filtered through a filter, so that most characteristic voiceprint signals can be reserved, and noise interference is eliminated.
The implementation principle is as follows: according to the method, voiceprint information of corresponding rotary mechanical equipment is collected on the spot, a voiceprint database is processed and established, meanwhile, a characteristic neural network model for identifying normal operation voiceprint characteristics and classical fault voiceprint characteristics of the rotary machinery is trained according to the content of the voiceprint database, a plurality of audio collectors are deployed on the spot, the processed audio information is guided into the characteristic neural network model through an infinite communication module, health and fault characteristic identification are carried out, operation conditions of the rotary machinery are detected, abnormal alarms are collected, the database is corrected, unmanned automatic monitoring collection, automatic operation state analysis, automatic early warning, abnormal detection and collection are achieved, one period conversion and data fusion are carried out for three seconds, large quantities of data are calculated and judged in real time, the efficiency of data processing judgment is improved, the time of detection response after faults occur is reduced, guarantee of safe operation of the equipment is greatly improved, workers do not need to enter a dangerous space in the whole process, detection standards are more accurate, detection results are kept and analyzed, unmanned monitoring, automatic early warning and high automation degree is achieved in the whole process.
Claims (9)
1. A rotating machinery health and fault feature recognition method based on audio technology is characterized by comprising the following steps;
s1: collecting voiceprint information of the rotating machinery through an audio collector on the spot, establishing a voiceprint database by collecting N groups of voiceprint frequency spectrums within fixed time, wherein the database comprises normal operation voiceprint characteristics and classical failure voiceprint characteristics, and preprocessing data after collection;
s2: constructing a neural network model, establishing a training model, repeatedly carrying out operation training on the training model through a plurality of collected classical sound frequency spectrums to be recognized to obtain a characteristic neural network model, optimizing recognition parameters, recognizing normal operation voiceprint characteristics and classical fault voiceprint characteristics by the characteristic neural network model, establishing a data processing platform, and comprehensively planning remote signaling, remote measurement, remote sensing data and acoustic time sequence data;
s3: deploying a plurality of audio collectors on the spot, adopting corrosion-resistant high-temperature-resistant high-pressure-resistant audio collecting equipment, attaching an infinite communication module on the audio collectors, synchronously collecting on-spot audio information according to time gradient, and preprocessing data after collection;
s4: the computer leads the on-site audio data into a characteristic neural network model, a data processing platform comprehensively and comprehensively plans remote signaling, remote sensing data and acoustic time sequence data to carry out health and fault characteristic identification, and simultaneously the computer displays the acquired frequency spectrum and frequency domain characteristic data on a display screen on the data processing platform in a real-time chart manner;
s5: judging whether the equipment operates normally or not according to the characteristic identification, and giving a warning if the equipment operates abnormally, and storing an abnormal record;
s6: after each warning, the system automatically records the monitoring data as a sample plate into a database according to whether the warning is mistaken and the severity is graded, and corrects the database again; for more serious accidents which may occur, the alarm can be given under the condition of lower confidence coefficient, the fault recording and displaying are carried out on the data processing platform, meanwhile, the operation information of each piece of equipment is comprehensively processed on the data processing platform, the health degree of the equipment is comprehensively judged, the information pushing is carried out in real time through the internet, associated apps, short messages and telephone channels, the online diagnosis of difficulties is realized through the internet, and the further decision making of a manager is facilitated.
2. The method for identifying health and fault characteristics of rotating machinery based on audio technology as claimed in claim 1, wherein in step S1, the voiceprint characteristics are obtained by taking the sound intensity and sound pressure as main characteristics, the acquisition time is 3S, and the acquisition is followed by log transformation based on time-sequence signal processing.
3. The method for identifying the health and fault characteristics of the rotating machine based on the audio technology as claimed in claim 1, wherein in step S1, the voiceprint information of the rotating machine is collected, noise is unavoidably doped in the process of collecting a voiceprint sample in normal operation, partial noise is removed by a depth residual error network ResNet method, i.e. different thresholds are adopted to separate different noises, unimportant characteristics are noticed by a attention machine, and the noise is set to zero by a soft threshold function; important identification features are noticed through an attention mechanism and are reserved, so that the capability of extracting useful features from a noise-containing signal by a deep neural network is enhanced, namely, a contrast frequency spectrum is repeatedly analyzed, noise is removed, and the precision is improved.
4. The method for identifying the health and fault characteristics of the rotating machine based on the audio technology as claimed in claim 1, wherein in the step S2, optimizing the identification parameters comprises combining multiple groups of normal operation voiceprint characteristics and classical fault voiceprint characteristics into a test group, comparing and verifying the test group with the normal operation voiceprint characteristics and the classical fault voiceprint sample characteristics in the neural network model, capturing a characteristic frequency spectrum, obtaining the characteristic neural network model if the verification is passed through by adopting an automatic parameter searching method, and continuing to construct the neural network model in the step S2 if the verification is not passed through, and establishing the training model until the accuracy requirement is met.
5. The method for identifying the health and fault characteristics of the rotating machinery based on the audio technology as claimed in claim 3, wherein in the step S3, the data is preprocessed after the field audio information is collected, and the processing mode is the same as that of removing part of the noise by using a ResNet method through a deep residual error network in the step S1.
6. The method for identifying the health and fault characteristics of the rotating machine based on the audio technology as claimed in claim 5, wherein in the process of removing the noise, a voice print of a person and a commonly used maintenance voice print are additionally introduced for removing, so that the interference of the person and the maintenance work sound is eliminated.
7. The method for identifying the health and fault characteristics of the rotating machinery based on the audio technology as claimed in claim 1, wherein in step S3, a plurality of audio collectors synchronously collect audio, the audio is collected synchronously according to the collection time of 3S each time, and the audio is collected and then subjected to logarithmic transformation based on time-sequence signal processing.
8. The method for identifying the health and fault characteristics of the rotating machine based on the audio technology as claimed in claim 1, wherein in the step S5, the warning mode is a plurality of reasonable combinations of short messages, telephone calls, lights and audio.
9. The method for identifying the health and fault characteristics of the rotating machine based on the audio technology as claimed in claim 1, wherein in the step S1, when the information of the early database is insufficient, the data is extended by linearly combining the collected data of the plurality of audio collectors and adding noise, so as to increase the data volume.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210828173.7A CN115238121A (en) | 2022-07-14 | 2022-07-14 | Rotating machine health and fault feature identification method based on audio technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210828173.7A CN115238121A (en) | 2022-07-14 | 2022-07-14 | Rotating machine health and fault feature identification method based on audio technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115238121A true CN115238121A (en) | 2022-10-25 |
Family
ID=83674364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210828173.7A Pending CN115238121A (en) | 2022-07-14 | 2022-07-14 | Rotating machine health and fault feature identification method based on audio technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115238121A (en) |
-
2022
- 2022-07-14 CN CN202210828173.7A patent/CN115238121A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112925279A (en) | Fault comprehensive analysis system based on MES system | |
| CN112504673B (en) | Carrier roller fault diagnosis method, system and storage medium based on machine learning | |
| US20230162484A1 (en) | Apparatus and method for generating learning data for artificial intelligence model | |
| CN112660745A (en) | Intelligent diagnosis method and system for carrier roller fault and readable storage medium | |
| CN113806969B (en) | Compressor unit health prediction method based on time domain data correlation modeling | |
| CN113982850B (en) | Fan comprehensive health analysis method and system integrating high-low frequency signals | |
| CN113739837A (en) | State prediction processing system of standard instrument | |
| CN116383633A (en) | Method and system for detecting faults of machine-made sand vibrating screen through multi-factor comprehensive analysis | |
| CN115437358A (en) | Intelligent state monitoring and fault diagnosis system and fault diagnosis method for industrial robot | |
| CN116861369A (en) | Air compressor health assessment method and system for industrial internet heterogeneous data fusion | |
| CN109598309B (en) | Detection system and monitoring method of metal packaging punching machine | |
| CN117251812A (en) | High-voltage power line operation fault detection method based on big data analysis | |
| CN113267601B (en) | Industrial production environment remote real-time monitoring cloud platform based on machine vision and data analysis | |
| CN113671911A (en) | Production condition monitoring system | |
| CN107506832B (en) | Hidden danger mining method for assisting monitoring tour | |
| CN108613820A (en) | A kind of online allophone monitoring algorithm for GIS bulk mechanicals defect diagonsis and positioning | |
| CN112365186A (en) | Health degree evaluation method and system for electric power information system | |
| CN115238121A (en) | Rotating machine health and fault feature identification method based on audio technology | |
| CN109115271B (en) | Digit control machine tool remote monitoring system | |
| CN116380468A (en) | Fault detection system for intelligent wharf and construction method | |
| CN116434368A (en) | Multifunctional handheld inspection instrument and inspection method | |
| CN113487189A (en) | Petrochemical equipment fault probability risk assessment system and assessment method | |
| CN112660746A (en) | Roller fault diagnosis method and system based on big data technology and storage medium | |
| CN114565883A (en) | Graphic recognition algorithm for operation faults of equipment | |
| CN112814890A (en) | Method for detecting pump machine fault based on voiceprint and vibration |
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 |