CN114034378A - Acoustic fault diagnosis system based on Internet of things - Google Patents
Acoustic fault diagnosis system based on Internet of things Download PDFInfo
- Publication number
- CN114034378A CN114034378A CN202111070984.7A CN202111070984A CN114034378A CN 114034378 A CN114034378 A CN 114034378A CN 202111070984 A CN202111070984 A CN 202111070984A CN 114034378 A CN114034378 A CN 114034378A
- Authority
- CN
- China
- Prior art keywords
- signal
- signals
- fault
- acoustic
- normal
- 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.)
- Withdrawn
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 25
- 238000000926 separation method Methods 0.000 claims abstract description 23
- 230000002159 abnormal effect Effects 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims abstract description 6
- 238000001514 detection method Methods 0.000 claims abstract description 4
- 238000003672 processing method Methods 0.000 claims abstract description 4
- 230000005236 sound signal Effects 0.000 claims description 18
- 238000005311 autocorrelation function Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000005204 segregation Methods 0.000 claims 1
- 238000000605 extraction Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses an acoustic fault diagnosis system based on the Internet of things, which comprises a fault database, a normal background sound database, a fault signal AI separation model and signal acquisition and detection equipment, wherein the fault database comprises: a fault database: the fault acoustic signal processing method comprises the existing fault acoustic signal and can memorize the existing fault acoustic signal; normal background sound database: including existing normal background acoustic signals; a fault signal AI separation model, which is constructed according to the existing fault and normal signals; signal acquisition check out test set: the method is used for acquiring the normal operation acoustic signals of the equipment, blind separation is carried out by taking the normal signals as extraction objects, fine tuning is carried out on the site to obtain a customized model for extracting the normal signals of the site, similarity analysis is carried out on the signals remained after the normal signals are extracted, and if the signals have similarity or periodicity in a time domain, the signals are judged to be abnormal.
Description
Technical Field
The invention relates to a fault diagnosis system, in particular to an acoustic fault diagnosis system based on the Internet of things, and belongs to the technical field of acoustic diagnosis.
Background
The process of finding whether a system and equipment have faults is fault diagnosis by utilizing various checking and testing methods; the process of further determining the approximate position of the fault belongs to the field of network survivability, fault diagnosis and fault location belong to the field of network survivability, the process of locating the fault to the replaceable product level when repair is carried out is required to be called fault isolation, and the fault diagnosis refers to the process of fault detection and fault isolation.
The existing fault diagnosis model based on the acoustic signal mainly judges whether equipment has faults by comparing the collected equipment acoustic signal with the existing fault acoustic signal, such as voiceprint comparison, certain noise reduction is carried out during collection, background noise which is not the equipment sound is reduced, the signal-to-noise ratio of the equipment sound is improved, the equipment sound can be compared with the fault acoustic signal more effectively, however, whether the equipment is in an abnormal state cannot be judged under the condition of few fault samples, and therefore the acoustic fault diagnosis system based on the internet of things is provided.
Disclosure of Invention
The invention aims to provide an acoustic fault diagnosis system based on the Internet of things, and the acoustic fault diagnosis system is used for solving the problem that whether equipment is in an abnormal state or not can be judged under the condition of few fault samples in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: acoustic fault diagnosis system based on thing networking, acoustic fault diagnosis system includes trouble database, normal background sound database, trouble signal AI separation model and signal acquisition check out test set, wherein:
a fault database: the fault acoustic signal processing method comprises the existing fault acoustic signal and can memorize the existing fault acoustic signal;
normal background sound database: including existing normal background acoustic signals;
a fault signal AI separation model, which is constructed according to the existing fault and normal signals;
signal acquisition check out test set: for acquiring normal operating acoustic signals of the device.
As a preferred technical solution of the present invention, the construction of the fault signal AI separation model includes the following contents:
s1: mixing the normal operation acoustic signal and the interference acoustic signal of the equipment into a background acoustic signal;
s2: various fault sound signals are obtained through a Dirac function and a room impulse response set, and are mixed with background sound signals to form mixed sound signals;
s3: the actually collected signal and the mixed sound signal are mixed and finely adjusted to be separated by a separation network, and the normal part and the abnormal part of the field signal are extracted after fine adjustment.
As a preferred technical solution of the present invention, the disturbing sound signal is composed of an ambient sound signal and a human sound signal.
As a preferred technical solution of the present invention, the similarity analysis includes the following:
the similarity between the signal times is calculated by a method of calculating an autocorrelation function,
R_f(τ)＝∫-∞ ∞f(t)f*(t+τ)dt
wherein: and f (t) is a signal, a conjugate is taken, tau is time delay, R _ f (tau) has obvious periodicity in a time domain, so that the signal has high repeatability in time, and the obtained signal can be judged to be an abnormal sound signal.
As a preferred technical scheme, the use method of the acoustic fault diagnosis system based on the Internet of things comprises the following steps:
the first step is as follows: establishing an AI separation model according to the existing fault signal and the normal signal;
the second step is that: carrying out mixing fine adjustment on the AI separation model by using the signals acquired on site and the original signals;
the third step: extracting a normal part and an abnormal part of the field signal based on the fine-tuned model;
the fourth step: and performing similarity analysis by using the signals of the abnormal part, judging whether the signals are faults if the signals are not similar signals, judging whether the signals are abnormal sounds if the signals are similar signals, and comparing the signals with a fault database to judge the type of the faults.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the acoustic fault diagnosis system based on the Internet of things, the normal signals are taken as extraction objects to be separated blindly, fine tuning is carried out on the site to obtain a customized model for extracting the normal signals of the site, similarity analysis is carried out on the signals remained after the normal signals are extracted, and if the signals have similarity or periodicity in a time domain, the signals are judged to be abnormal.
Drawings
FIG. 1 is a schematic flow diagram of a diagnostic system of the present invention;
FIG. 2 is a schematic diagram of a modeling process of the AI separation model according to the invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
Referring to fig. 1-2, the present invention provides a technical solution of an acoustic fault diagnosis system based on the internet of things:
as shown in fig. 1-2, the acoustic fault diagnosis system includes a fault database, a normal background sound database, a fault signal AI separation model, and a signal acquisition and detection device, wherein:
a fault database: the fault acoustic signal processing method comprises the existing fault acoustic signal and can memorize the existing fault acoustic signal;
normal background sound database: including existing normal background acoustic signals;
a fault signal AI separation model, which is constructed according to the existing fault and normal signals;
signal acquisition check out test set: for acquiring normal operating acoustic signals of the device.
The construction of the fault signal AI separation model comprises the following steps:
s1: mixing the normal operation acoustic signal and the interference acoustic signal of the equipment into a background acoustic signal;
s2: various fault sound signals are obtained through a Dirac function and a room impulse response set, and are mixed with background sound signals to form mixed sound signals;
s3: the actually collected signal and the mixed sound signal are mixed and finely adjusted to be separated by a separation network, and the normal part and the abnormal part of the field signal are extracted after fine adjustment.
The disturbing acoustic signal is composed of an ambient acoustic signal and a human acoustic signal.
The similarity analysis includes the following:
the similarity between the signal times is calculated by a method of calculating an autocorrelation function,
R_f(τ)＝∫-∞ ∞f(t)f*(t+τ)dt
wherein: and f (t) is a signal, a conjugate is taken, tau is time delay, R _ f (tau) has obvious periodicity in a time domain, so that the signal has high repeatability in time, and the obtained signal can be judged to be an abnormal sound signal.
The use method of the acoustic fault diagnosis system based on the Internet of things comprises the following steps:
the first step is as follows: establishing an AI separation model according to the existing fault signal and the normal signal;
the second step is that: carrying out mixing fine adjustment on the AI separation model by using the signals acquired on site and the original signals;
the third step: extracting a normal part and an abnormal part of the field signal based on the fine-tuned model;
the fourth step: and performing similarity analysis by using the signals of the abnormal part, judging whether the signals are faults if the signals are not similar signals, judging whether the signals are abnormal sounds if the signals are similar signals, and comparing the signals with a fault database to judge the type of the faults.
When the system is used specifically, an AI separation model is constructed according to the existing fault signal and the normal signal; carrying out mixing fine adjustment on the AI separation model by using the signals acquired on site and the original signals; extracting a normal part and an abnormal part of the field signal based on the fine-tuned model; the method comprises the steps of utilizing signals of an abnormal part to carry out similarity analysis, judging whether the signals are faults or not if the signals are not similar signals, judging whether the signals are abnormal sounds or not if the signals are similar signals, comparing the signals with a fault database to judge fault types.
In the description of the present invention, it is to be understood that the indicated orientations or positional relationships are based on the orientations or positional relationships shown in the drawings and are only for convenience in describing the present invention and simplifying the description, but are not intended to indicate or imply that the indicated devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are not to be construed as limiting the present invention.
In the present invention, unless otherwise explicitly specified or limited, for example, it may be fixedly attached, detachably attached, or integrated; can be mechanically or electrically connected; the terms may be directly connected or indirectly connected through an intermediate, and may be communication between two elements or interaction relationship between two elements, unless otherwise specifically limited, and the specific meaning of the terms in the present invention will be understood by those skilled in the art according to specific situations.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. Acoustic fault diagnosis system based on Internet of things is characterized by comprising a fault database, a normal background sound database, a fault signal AI separation model and signal acquisition and detection equipment, wherein:
a fault database: the fault acoustic signal processing method comprises the existing fault acoustic signal and can memorize the existing fault acoustic signal;
normal background sound database: including existing normal background acoustic signals;
a fault signal AI separation model, which is constructed according to the existing fault and normal signals;
signal acquisition check out test set: for acquiring normal operating acoustic signals of the device.
2. The internet of things-based acoustic fault diagnosis system of claim 1, wherein the construction of the fault signal AI segregation model comprises the following:
s1: mixing the normal operation acoustic signal and the interference acoustic signal of the equipment into a background acoustic signal;
s2: various fault sound signals are obtained through a Dirac function and a room impulse response set, and are mixed with background sound signals to form mixed sound signals;
s3: the actually collected signal and the mixed sound signal are mixed and finely adjusted to be separated by a separation network, and the normal part and the abnormal part of the field signal are extracted after fine adjustment.
3. The internet of things-based acoustic fault diagnosis system of claim 2, wherein the disturbing acoustic signal is composed of an ambient acoustic signal and a human acoustic signal.
4. The internet of things-based acoustic fault diagnosis system of claim 1, wherein the similarity analysis comprises the following:
the similarity between the signal times is calculated by a method of calculating an autocorrelation function,
R_f(τ)＝∫-∞ ∞f(t)f*(t+τ)dt
wherein: and f (t) is a signal, a conjugate is taken, tau is time delay, R _ f (tau) has obvious periodicity in a time domain, so that the signal has high repeatability in time, and the obtained signal can be judged to be an abnormal sound signal.
5. The use method of the acoustic fault diagnosis system based on the Internet of things is characterized by comprising the following steps:
the first step is as follows: establishing an AI separation model according to the existing fault signal and the normal signal;
the second step is that: carrying out mixing fine adjustment on the AI separation model by using the signals acquired on site and the original signals;
the third step: extracting a normal part and an abnormal part of the field signal based on the fine-tuned model;
the fourth step: and performing similarity analysis by using the signals of the abnormal part, judging whether the signals are faults if the signals are not similar signals, judging whether the signals are abnormal sounds if the signals are similar signals, and comparing the signals with a fault database to judge the type of the faults.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111070984.7A CN114034378A (en) | 2021-09-13 | 2021-09-13 | Acoustic fault diagnosis system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111070984.7A CN114034378A (en) | 2021-09-13 | 2021-09-13 | Acoustic fault diagnosis system based on Internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114034378A true CN114034378A (en) | 2022-02-11 |
Family
ID=80134378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111070984.7A Withdrawn CN114034378A (en) | 2021-09-13 | 2021-09-13 | Acoustic fault diagnosis system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114034378A (en) |
-
2021
- 2021-09-13 CN CN202111070984.7A patent/CN114034378A/en not_active Withdrawn
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106546892A (en) | The recognition methodss of shelf depreciation ultrasonic audio and system based on deep learning | |
| CN110160791A (en) | Based on small echo-spectrum kurtosis induction machine bearing failure diagnosis system and diagnostic method | |
| CN110335617A (en) | A kind of noise analysis method in substation | |
| CN110031088A (en) | Electronic failure detection method, device, equipment and range hood | |
| CN105448303A (en) | Voice signal processing method and apparatus | |
| CN107571816A (en) | Method and apparatus for detecting vehicle mechanical failure | |
| EP1843564A1 (en) | Communication line diagnostics tool and method detecting synchronized/ correlated anomalies | |
| CN104048165B (en) | The method of pipeline leakage diagnosis | |
| CN106019089A (en) | Method for carrying out partial discharging determination based on related relationship feature of alternate signals | |
| CN114034378A (en) | Acoustic fault diagnosis system based on Internet of things | |
| CN111879479B (en) | Micro-leakage signal monitoring system and method for non-Gaussian noise environment of gas collecting and conveying pipeline | |
| CN106646021B (en) | A kind of Kato detection method and device | |
| CN113295346A (en) | Valve internal leakage detection method based on sound waves | |
| CN116961799A (en) | Signal interference detection method based on time-frequency domain distribution characteristics | |
| CN112927720B (en) | Audio anomaly detection method and device | |
| CN109884483A (en) | Insulating tube type busbar shelf depreciation acoustics on-line monitoring method and device | |
| CN108846106A (en) | A kind of method and apparatus for judging to whether there is identical audio in multiple audios | |
| CN105788173A (en) | Sleep monitoring method and sleep monitoring apparatus | |
| CN112345648B (en) | High-voltage circuit breaker cam crack fault detection device and method | |
| CN108919068A (en) | Power equipment intermittent defect signal recognition method | |
| CN205620145U (en) | Equipment trouble acoustic frequency detecting system | |
| CN114118166A (en) | Transformer fault diagnosis system and method based on intelligent frequency spectrum monitoring | |
| CN110703080B (en) | GIS spike discharge diagnosis method, discharge degree identification method and device | |
| CN112087703A (en) | Audio acquisition fault diagnosis method for audio monitor | |
| CN205750522U (en) | Diagnostic trouble code testing tool |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220211 |