CN111948295A - Fault detection system based on sound waves and motor fault detection method - Google Patents
Fault detection system based on sound waves and motor fault detection method Download PDFInfo
- Publication number
- CN111948295A CN111948295A CN202010838160.9A CN202010838160A CN111948295A CN 111948295 A CN111948295 A CN 111948295A CN 202010838160 A CN202010838160 A CN 202010838160A CN 111948295 A CN111948295 A CN 111948295A
- Authority
- CN
- China
- Prior art keywords
- motor
- sound wave
- data
- fault
- average value
- 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/14—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object using acoustic emission techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/449—Statistical methods not provided for in G01N29/4409, e.g. averaging, smoothing and interpolation
-
- G—PHYSICS
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C17/00—Arrangements for transmitting signals characterised by the use of a wireless electrical link
- G08C17/02—Arrangements for transmitting signals characterised by the use of a wireless electrical link using a radio link
Abstract
The invention provides a fault detection system and a motor fault detection method based on sound waves, which are used for solving the problems that motor fault detection is difficult and expert is needed to accurately judge in the prior art. To achieve the above and other related objects, the present invention provides an acoustic wave based fault detection system, comprising: the sound wave acquisition terminal is used for carrying out sound wave acquisition on the motors in the motor group independently; the sound wave acquisition terminal comprises sound wave detection sensors and a wireless communication module, the sound wave detection sensors are used for acquiring sound wave data generated by vibration of corresponding motors, one motor corresponds to a plurality of sound wave detection sensors, the sound wave detection sensors are arranged at different positions on the motor, and the wireless transmission module is used for transmitting the sound wave data corresponding to the motor; and the cloud server can receive the sound wave data transmitted by the wireless communication module and judge whether the corresponding motor is in a fault state.
Description
Technical Field
The invention relates to the field of motor fault detection, in particular to a fault detection system based on sound waves and a motor fault detection method.
Background
The motor fault detection adopted in a factory at present adopts a stethoscope for diagnosis, and has the problems that 1, the fault detection is carried out manually, errors exist, a detector needs to have rich experience, and the fault detection is carried out in a noisy environment in the factory in an auscultation mode with great difficulty. 2. Auscultation faults are often diagnosed by abnormalities caused by tiny faults of the motor, and the abnormalities cannot be detected by common workers, but the faults of the motor cannot be detected frequently, and can only be detected periodically, so that the motor faults cannot be found timely.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide a fault detection system and a fault detection method based on sound waves, which are used to solve the problems of difficulty in detecting a fault of a motor and requiring an expert to accurately determine the fault.
To achieve the above and other related objects, the present invention provides an acoustic wave based fault detection system, comprising:
the sound wave acquisition terminal is used for carrying out sound wave acquisition on the motors in the motor group independently;
the sound wave acquisition terminal comprises sound wave detection sensors and a wireless communication module, the sound wave detection sensors are used for acquiring sound wave data generated by vibration of corresponding motors, one motor corresponds to a plurality of sound wave detection sensors, the sound wave detection sensors are arranged at different positions on the motor, and the wireless transmission module is used for transmitting the sound wave data corresponding to the motor;
and the cloud server can receive the sound wave data transmitted by the wireless communication module and judge whether the corresponding motor is in a fault state.
Optionally, each of the acoustic wave detection sensors is arranged in the circumferential direction of the motor, each of the acoustic wave detection sensors is electrically connected to an offline acquisition module, the offline acquisition module is configured to receive acoustic wave data of a plurality of acoustic wave detection sensors of a single motor, and remove abnormal data from the acoustic wave data, when data of the plurality of acoustic wave detection sensors are similar, an average value is fitted, and the fitted average value is transmitted to the cloud server through the wireless communication module; when a small part of data in the data of the acoustic wave detection sensors is abnormal to a large part of data, the abnormal data in the data are removed, an average value is fitted to the rest data, and the fitted average value is transmitted to the cloud server through the wireless communication module.
Optionally, the offline acquisition module includes a power supply unit and a processing unit, the power supply unit is configured to provide power for the processing unit, and the processing unit is configured to perform abnormal data elimination processing on the sound wave data of a single motor and fit an average value to the remaining data.
Optionally, the offline acquisition module further includes a storage unit, and the storage unit is configured to record the fitting average value of the processing unit in real time.
Optionally, the fitting average of the storage unit is periodically transmitted to the cloud server through the wireless communication module.
Optionally, the sound wave detection sensors are arranged in the circumferential direction of the motor, the cloud server is configured to receive sound wave data of each motor, the cloud server performs abnormal data elimination on the sound wave data of the sound wave detection sensors of a single motor, when the data of the sound wave detection sensors are similar, an average value is fitted, and the fitted average value is transmitted to the cloud server through the wireless communication module; when a small part of data in the data of the acoustic wave detection sensors is abnormal to a large part of data, the abnormal data in the data are removed, an average value is fitted to the rest data, and the fitted average value is transmitted to the cloud server through the wireless communication module.
Optionally, still include first temperature sensor and second temperature sensor, first temperature sensor is used for gathering the surface temperature of motor, the second passes temperature sensor and is used for gathering the temperature of the environment that the motor is located, first temperature sensor with second temperature sensor all transmits temperature data for cloud server through wireless communication module.
Optionally, the cloud server is further configured to compare the temperature data of the first temperature sensor and the second temperature sensor with the temperature sample.
A motor fault detection method comprises the following steps:
the method comprises the following steps of firstly, establishing sound wave samples and carrying out different scene training on the sound wave samples, removing abnormal data from a plurality of sound wave data in the circumferential direction of a motor and fitting an average value, wherein the training process is as follows:
establishing a sound wave sample of a normal motor, collecting a plurality of sound wave data in the circumferential direction of the normal motor, removing abnormal data and fitting an average value;
establishing a sound wave sample in the process that the phase-lack motor is changed from a normal state to a fault state, collecting a plurality of sound wave data in the circumferential direction of the phase-lack motor, eliminating abnormal data and fitting an average value;
establishing a sound wave sample in the process that the overload motor is changed from a normal state to a fault state, collecting a plurality of sound wave data on the circumferential direction of the overload motor, eliminating abnormal data and fitting an average value;
establishing a sound wave sample in the process that the inter-turn motor is changed from a normal state to a fault state, collecting a plurality of sound wave data on the circumferential direction of the inter-turn motor, eliminating abnormal data and fitting an average value;
establishing a sound wave sample in the process that the interphase motor is changed from a normal state to a fault state, collecting a plurality of sound wave data in the circumferential direction of the interphase motor, eliminating abnormal data and fitting an average value;
establishing a sound wave sample of the ground impact motor, collecting a plurality of sound wave data in the circumferential direction of the ground impact motor, removing abnormal data and fitting an average value;
and secondly, rejecting abnormal data and fitting an average value from a plurality of real-time sound wave data in the circumferential direction of the motor, comparing the real-time fitting average value of the corresponding motor with the sound wave sample, and judging whether the motor fails and the type of the failure.
Optionally, the first step further includes establishing a temperature sample and performing different scene training on the temperature sample, where the training process is as follows:
establishing a normal motor temperature sample, and acquiring temperature data of the normal motor continuously working at different environmental temperatures;
establishing a temperature sample of the phase-failure motor in the process of changing from a normal state to a fault state, and acquiring temperature data of the phase-failure motor in the process of changing from the normal state to the fault state under different environmental temperatures;
establishing a temperature sample of the overload motor in the process of changing from a normal state to a fault state, and acquiring temperature data of the overload motor in the process of changing from the normal state to the fault state under different environmental temperatures;
establishing a temperature sample of the inter-turn motor in the process of changing from a normal state to a fault state, and acquiring temperature data of the inter-turn motor in the process of changing from the normal state to the fault state under different environmental temperatures;
establishing a temperature sample of the phase-to-phase motor in the process of changing from a normal state to a fault state, and acquiring temperature data of the phase-to-phase motor in the process of changing from the normal state to the fault state under different environmental temperatures;
establishing a ground fault motor temperature sample, and collecting temperature data of the ground fault motor in the process of changing from a normal state to a fault state under different environmental temperatures;
after the third step, the method also comprises a fourth step:
comparing the real-time temperature data of the corresponding motor with the temperature sample, and secondarily judging whether the motor fails and the type of the failure;
when the fault states judged in the second step and the fourth step are consistent, sending fault early warning or fault prompt of the corresponding motor;
and when the fault conditions judged in the second step and the fourth step are inconsistent, prompting to send out a prompt for waiting for checking of the corresponding motor.
As described above, the fault detection system and the motor fault detection method based on sound waves of the present invention have at least the following beneficial effects:
the motor is subjected to fault detection in a sound wave mode, monitoring analysis is performed in a cloud server mode, motor fault detection cost is greatly saved, unmanned monitoring in the whole process is achieved, sound wave detection sensors are arranged in the circumferential direction of the motor, abnormal data are eliminated in the processing process, the influence of measurement errors of a single sound wave detection sensor or local measurement errors of the motor can be avoided, and therefore accuracy of data acquisition can be guaranteed; through the training to the different scenes of sound wave sample for can judge its fault type through the sound wave, judge more accurately, and have pertinence, can directly carry out the fault maintenance when workman maintains the motor.
Drawings
Fig. 1 is a schematic diagram of a first embodiment of an acoustic wave based fault detection system of the present invention.
Fig. 2 is a schematic diagram of a second embodiment of the acoustic wave based fault detection system of the present invention.
Element number description:
Detailed Description
The following description of the embodiments of the present invention is provided for illustrative purposes, and other advantages and effects of the present invention will become apparent to those skilled in the art from the present disclosure.
The following examples are for illustrative purposes only. The various embodiments may be combined, and are not limited to what is presented in the following single embodiment.
Referring to fig. 1 and 2, an embodiment of a fault detection system based on acoustic waves according to the present invention includes: the system comprises a sound wave acquisition terminal and a cloud server, wherein the sound wave acquisition terminal is used for individually acquiring sound waves of motors in a motor group; the sound wave acquisition terminal comprises sound wave detection sensors and a wireless communication module, the sound wave detection sensors are used for acquiring sound wave data generated by vibration of corresponding motors, one motor corresponds to a plurality of sound wave detection sensors, the sound wave detection sensors are arranged at different positions on the motor, and the wireless transmission module is used for transmitting the sound wave data corresponding to the motor; the cloud server can receive the sound wave data transmitted by the wireless communication module and judge whether the corresponding motor is in a fault state.
In this embodiment, please refer to fig. 2, the acoustic wave detection sensors are arranged in the circumferential direction of the motor, and are electrically connected to an offline acquisition module, where the offline acquisition module is configured to receive acoustic wave data of a plurality of acoustic wave detection sensors of a single motor, and remove abnormal data from the acoustic wave data, and when data of the plurality of acoustic wave detection sensors are close to each other, fit an average value, and transmit the fit average value to the cloud server through the wireless communication module; when a small part of data in the data of the acoustic wave detection sensors is abnormal to a large part of data, the abnormal data in the data are removed, an average value is fitted to the rest data, and the fitted average value is transmitted to the cloud server through the wireless communication module.
In this embodiment, referring to fig. 2, the offline acquisition module includes a power supply unit and a processing unit, the power supply unit is configured to provide power for the processing unit, and the processing unit is configured to perform abnormal data elimination processing on the sound wave data of a single motor and fit an average value to the remaining data.
In this embodiment, referring to fig. 2, the offline acquisition module further includes a storage unit, and the storage unit is configured to record the fitting average value of the processing unit in real time. Optionally, the fitting average of the storage unit is periodically transmitted to the cloud server through the wireless communication module. The data of each motor is subjected to independent fault judgment and processing, the recorded data are stored at the same time, data transmission of the cloud server and the units at all places is waited, the cloud server sorts the data after receiving the data, if the motor fault data are recorded, fault prompts corresponding to the motors are sent out, the purpose of doing so is that the data do not need to pass in real time, periodic communication is adopted, offline processing can be achieved, and meanwhile the working state of the motors can be completely known when the data are on line.
In this embodiment, please refer to fig. 1, the sound wave detection sensors are arranged in the circumferential direction of the motor, the cloud server is configured to receive sound wave data of the motors, the cloud server performs abnormal data elimination on the sound wave data of the sound wave detection sensors of a single motor, and when the data of the sound wave detection sensors are close to each other, an average value is fitted, and the fitted average value is transmitted to the cloud server through the wireless communication module; when a small part of data in the data of the acoustic wave detection sensors is abnormal to a large part of data, the abnormal data in the data are removed, an average value is fitted to the rest data, and the fitted average value is transmitted to the cloud server through the wireless communication module. Carry out the operation analysis through the cloud ware, can improve the operational capability, it is less simultaneously in the required power of motor department sensor and wireless communication module, improve the duration of battery, if handle the operation through online down, firstly the electric quantity consumption grow needs frequently to be changed the battery, and it is inconvenient to maintain when producing the trouble to the downward processing unit simultaneously, through the operation of cloud ware, can reduce fortune dimension cost.
In this embodiment, please refer to fig. 1 and 2, the system further includes a first temperature sensor and a second temperature sensor, the first temperature sensor is configured to acquire a surface temperature of the motor, the second temperature sensor is configured to acquire a temperature of an environment where the motor is located, and both the first temperature sensor and the second temperature sensor transmit temperature data to the cloud server through the wireless communication module. Optionally, the cloud server is further configured to compare the temperature data of the first temperature sensor and the second temperature sensor with the temperature sample. Because during the motor trouble, especially transship, its temperature can rise, if lack the looks the time, the heat normal operating can reduce again relatively, carries out supplementary verification through temperature sensor, can improve the precision of judging, simultaneously through the collection to ambient temperature, can realize judging the motor trouble emergence condition under the different temperature conditions.
A motor fault detection method comprises the following steps:
the method comprises the following steps of firstly, establishing sound wave samples and carrying out different scene training on the sound wave samples, removing abnormal data from a plurality of sound wave data in the circumferential direction of a motor and fitting an average value, wherein the training process is as follows:
establishing a sound wave sample of a normal motor, collecting a plurality of sound wave data in the circumferential direction of the normal motor, removing abnormal data and fitting an average value;
establishing a sound wave sample in the process that the phase-lack motor is changed from a normal state to a fault state, collecting a plurality of sound wave data in the circumferential direction of the phase-lack motor, eliminating abnormal data and fitting an average value;
establishing a sound wave sample in the process that the overload motor is changed from a normal state to a fault state, collecting a plurality of sound wave data on the circumferential direction of the overload motor, eliminating abnormal data and fitting an average value;
establishing a sound wave sample in the process that the inter-turn motor is changed from a normal state to a fault state, collecting a plurality of sound wave data on the circumferential direction of the inter-turn motor, eliminating abnormal data and fitting an average value;
establishing a sound wave sample in the process that the interphase motor is changed from a normal state to a fault state, collecting a plurality of sound wave data in the circumferential direction of the interphase motor, eliminating abnormal data and fitting an average value;
establishing a sound wave sample of the ground impact motor, collecting a plurality of sound wave data in the circumferential direction of the ground impact motor, removing abnormal data and fitting an average value;
and secondly, rejecting abnormal data and fitting an average value from a plurality of real-time sound wave data in the circumferential direction of the motor, comparing the real-time fitting average value of the corresponding motor with the sound wave sample, and judging whether the motor fails and the type of the failure.
The sound wave sample is trained in a machine learning mode, so that whether the sound wave sample breaks down or not can be judged more accurately, sound wave change before the displacement fault is recorded and trained, and the system can predict and judge that some fault or several faults are about to occur before the fault occurs, so that early warning is performed in advance.
In this embodiment, on the basis of the first step of the previous embodiment, the method further includes establishing a temperature sample and performing different scene training on the temperature sample, wherein the training process is as follows:
establishing a normal motor temperature sample, and acquiring temperature data of the normal motor continuously working at different environmental temperatures;
establishing a temperature sample of the phase-failure motor in the process of changing from a normal state to a fault state, and acquiring temperature data of the phase-failure motor in the process of changing from the normal state to the fault state under different environmental temperatures;
establishing a temperature sample of the overload motor in the process of changing from a normal state to a fault state, and acquiring temperature data of the overload motor in the process of changing from the normal state to the fault state under different environmental temperatures;
establishing a temperature sample of the inter-turn motor in the process of changing from a normal state to a fault state, and acquiring temperature data of the inter-turn motor in the process of changing from the normal state to the fault state under different environmental temperatures;
establishing a temperature sample of the phase-to-phase motor in the process of changing from a normal state to a fault state, and acquiring temperature data of the phase-to-phase motor in the process of changing from the normal state to the fault state under different environmental temperatures;
establishing a ground fault motor temperature sample, and collecting temperature data of the ground fault motor in the process of changing from a normal state to a fault state under different environmental temperatures;
after the third step, the method also comprises a fourth step:
comparing the real-time temperature data of the corresponding motor with the temperature sample, and secondarily judging whether the motor fails and the type of the failure;
when the fault states judged in the second step and the fourth step are consistent, sending fault early warning or fault prompt of the corresponding motor;
and when the fault conditions judged in the second step and the fourth step are inconsistent, prompting to send out a prompt for waiting for checking of the corresponding motor.
The intervention of the temperature condition enables the result of the sound wave judgment to be verified for the second time, for example, in a certain temperature change range, the result corresponds to one fault state or a plurality of fault states, and as long as the data result compared with the temperature sample is not contradictory with the comparison data result of the sound wave sample, the judgment of the comparison result of the sound wave sample is correct, and a fault prompt can be sent.
The motor failure may be:
phase loss, cause: generally, the power supply is caused by phase loss (one phase is not supplied with power or the power supply voltage is insufficient) or the contact point of the contactor in the circuit is not closed, the wire connection point is disconnected, and the contact is loosened or the contact position is oxidized. Is characterized in that: one or two phases (4 levels) in the winding are completely blackened, the coil is damaged symmetrically, and the phase is regularly absent.
Overload, reason: generally, the motor runs for a long time under current, runs in an overheating way, is frequently started or braked, and is also caused by wiring errors (delta connection into star connection). Is characterized in that: the windings all turn black and the end straps turn discolored and become brittle or even break.
Turn-to-turn, reason: and the enameled wire is broken due to the manufacturing process of the motor. Is characterized in that: the winding is partially burnt out, and the inner cavity of the motor is clean usually, and only one explosion point exists.
The reason is as follows: the interphase paper is not put in place, or the interphase paper (sleeve) is damaged. Is characterized in that: two adjacent phases of the motor are burnt.
Ground hit, reason: the distance between the coil and the end cover base is not enough. Is characterized in that: and black burning traces are arranged between the coil and the end cover or between the coil and the end cover.
In conclusion, the fault detection is carried out on the motor in the form of sound waves, the monitoring analysis is carried out in the form of the cloud server, the fault detection cost of the motor is greatly saved, the unmanned monitoring in the whole process is realized, and the sound wave detection sensors are arranged in the circumferential direction of the motor, and abnormal data are eliminated in the processing process, so that the influence of the measurement error of a single sound wave detection sensor or the local measurement error of the motor can be avoided, and the accuracy of data acquisition can be ensured; through the training to the different scenes of sound wave sample for can judge its fault type through the sound wave, judge more accurately, and have pertinence, can directly carry out the fault maintenance when workman maintains the motor.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. An acoustic-based fault detection system, comprising:
the sound wave acquisition terminal is used for carrying out sound wave acquisition on the motors in the motor group independently;
the sound wave acquisition terminal comprises sound wave detection sensors and a wireless communication module, the sound wave detection sensors are used for acquiring sound wave data generated by vibration of corresponding motors, one motor corresponds to a plurality of sound wave detection sensors, the sound wave detection sensors are arranged at different positions on the motor, and the wireless transmission module is used for transmitting the sound wave data corresponding to the motor;
and the cloud server can receive the sound wave data transmitted by the wireless communication module and judge whether the corresponding motor is in a fault state.
2. The acoustic-based fault detection system of claim 1, wherein: the sound wave detection sensors are arranged in the circumferential direction of the motor, and are electrically connected with an offline acquisition module, the offline acquisition module is used for receiving sound wave data of a plurality of sound wave detection sensors of a single motor and removing abnormal data of the sound wave data, when the data of the sound wave detection sensors are similar, an average value is fitted, and the fitted average value is transmitted to the cloud server through a wireless communication module; when a small part of data in the data of the acoustic wave detection sensors is abnormal to a large part of data, the abnormal data in the data are removed, an average value is fitted to the rest data, and the fitted average value is transmitted to the cloud server through the wireless communication module.
3. The acoustic-based fault detection system of claim 2, wherein: the off-line acquisition module comprises a power supply unit and a processing unit, the power supply unit is used for supplying power to the processing unit, and the processing unit is used for carrying out abnormal data removing processing on the sound wave data of the single motor and fitting an average value to the rest data.
4. The acoustic-based fault detection system of claim 3, wherein: the offline acquisition module further comprises a storage unit, and the storage unit is used for recording the fitting average value of the processing unit in real time.
5. The acoustic-based fault detection system of claim 4, wherein: and the fitting average value of the storage unit is periodically transmitted to the cloud server through the wireless communication module.
6. The acoustic-based fault detection system of claim 1, wherein: the cloud server is used for receiving sound wave data of the motors, performing abnormal data elimination on the sound wave data of the sound wave detection sensors of a single motor, fitting an average value when the data of the sound wave detection sensors are similar, and transmitting the fitted average value to the cloud server through the wireless communication module; when a small part of data in the data of the acoustic wave detection sensors is abnormal to a large part of data, the abnormal data in the data are removed, an average value is fitted to the rest data, and the fitted average value is transmitted to the cloud server through the wireless communication module.
7. An acoustic based fault detection system according to any of claims 1-6, wherein: still include first temperature sensor and second temperature sensor, first temperature sensor is used for gathering the surface temperature of motor, the second passes temperature sensor and is used for gathering the temperature of the environment that the motor is located, first temperature sensor with second temperature sensor all transmits temperature data for cloud ware through wireless communication module.
8. The acoustic-based fault detection system of claim 7, wherein: the cloud server is further used for comparing the temperature data of the first temperature sensor and the second temperature sensor with the temperature samples.
9. A motor fault detection method is characterized in that: the method comprises the following steps:
the method comprises the following steps of firstly, establishing sound wave samples and carrying out different scene training on the sound wave samples, removing abnormal data from a plurality of sound wave data in the circumferential direction of a motor and fitting an average value, wherein the training process is as follows:
establishing a sound wave sample of a normal motor, collecting a plurality of sound wave data in the circumferential direction of the normal motor, removing abnormal data and fitting an average value;
establishing a sound wave sample in the process that the phase-lack motor is changed from a normal state to a fault state, collecting a plurality of sound wave data in the circumferential direction of the phase-lack motor, eliminating abnormal data and fitting an average value;
establishing a sound wave sample in the process that the overload motor is changed from a normal state to a fault state, collecting a plurality of sound wave data on the circumferential direction of the overload motor, eliminating abnormal data and fitting an average value;
establishing a sound wave sample in the process that the inter-turn motor is changed from a normal state to a fault state, collecting a plurality of sound wave data on the circumferential direction of the inter-turn motor, eliminating abnormal data and fitting an average value;
establishing a sound wave sample in the process that the interphase motor is changed from a normal state to a fault state, collecting a plurality of sound wave data in the circumferential direction of the interphase motor, eliminating abnormal data and fitting an average value;
establishing a sound wave sample of the ground impact motor, collecting a plurality of sound wave data in the circumferential direction of the ground impact motor, removing abnormal data and fitting an average value;
and secondly, rejecting abnormal data and fitting an average value from a plurality of real-time sound wave data in the circumferential direction of the motor, comparing the real-time fitting average value of the corresponding motor with the sound wave sample, and judging whether the motor fails and the type of the failure.
10. The motor fault detection method of claim 9, wherein:
the first step, also include, set up the temperature sample and train it in different scenes, train the course as follows:
establishing a normal motor temperature sample, and acquiring temperature data of the normal motor continuously working at different environmental temperatures;
establishing a temperature sample of the phase-failure motor in the process of changing from a normal state to a fault state, and acquiring temperature data of the phase-failure motor in the process of changing from the normal state to the fault state under different environmental temperatures;
establishing a temperature sample of the overload motor in the process of changing from a normal state to a fault state, and acquiring temperature data of the overload motor in the process of changing from the normal state to the fault state under different environmental temperatures;
establishing a temperature sample of the inter-turn motor in the process of changing from a normal state to a fault state, and acquiring temperature data of the inter-turn motor in the process of changing from the normal state to the fault state under different environmental temperatures;
establishing a temperature sample of the phase-to-phase motor in the process of changing from a normal state to a fault state, and acquiring temperature data of the phase-to-phase motor in the process of changing from the normal state to the fault state under different environmental temperatures;
establishing a ground fault motor temperature sample, and collecting temperature data of the ground fault motor in the process of changing from a normal state to a fault state under different environmental temperatures;
after the third step, the method also comprises a fourth step:
comparing the real-time temperature data of the corresponding motor with the temperature sample, and secondarily judging whether the motor fails and the type of the failure;
when the fault states judged in the second step and the fourth step are consistent, sending fault early warning or fault prompt of the corresponding motor;
and when the fault conditions judged in the second step and the fourth step are inconsistent, prompting to send out a prompt for waiting for checking of the corresponding motor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010838160.9A CN111948295A (en) | 2020-08-19 | 2020-08-19 | Fault detection system based on sound waves and motor fault detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010838160.9A CN111948295A (en) | 2020-08-19 | 2020-08-19 | Fault detection system based on sound waves and motor fault detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111948295A true CN111948295A (en) | 2020-11-17 |
Family
ID=73358427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010838160.9A Pending CN111948295A (en) | 2020-08-19 | 2020-08-19 | Fault detection system based on sound waves and motor fault detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111948295A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114755611A (en) * | 2022-03-10 | 2022-07-15 | 重庆科创职业学院 | Sound wave-based detection method and device for turn-to-turn short circuit of oil-paper insulation transformer |
| CN115079042A (en) * | 2022-03-10 | 2022-09-20 | 重庆科创职业学院 | Sound wave-based transformer turn-to-turn short circuit detection and positioning method and device |
| CN116125275A (en) * | 2023-04-04 | 2023-05-16 | 常州市美特精密电机有限公司 | Reducing motor test system |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101226170A (en) * | 2007-12-26 | 2008-07-23 | 广东省建筑工程集团有限公司 | Method for detecting data aggregation judgment by foundation pile sound wave transmission method |
| CN101320018A (en) * | 2008-07-21 | 2008-12-10 | 哈尔滨工业大学 | Ultrasonic wave nondestructive apparatus and method for measuring residual stress of welded structure |
| CN101798957A (en) * | 2010-01-27 | 2010-08-11 | 北京信息科技大学 | Failure diagnosis method of power equipment |
| CN104596575A (en) * | 2014-12-25 | 2015-05-06 | 新疆新能钢结构有限责任公司 | Fan tower drum safe operation monitoring device and application method thereof |
| CN204615692U (en) * | 2015-05-12 | 2015-09-02 | 安徽理工大学 | Based on the supersonic motor measured operating parameter system of DSP |
| CN205404325U (en) * | 2016-02-17 | 2016-07-27 | 淮海工学院 | Indoor outstanding husky concentration calibration device |
| CN106124193A (en) * | 2016-05-30 | 2016-11-16 | 宁波诺丁汉大学 | Gearbox fault detection method in conjunction with vibrations with sound wave monitoring |
| CN108021064A (en) * | 2017-12-06 | 2018-05-11 | 合肥沙泰机电科技有限公司 | A kind of power-equipment health status inline diagnosis method |
| CN109085811A (en) * | 2018-10-11 | 2018-12-25 | 中国长城葡萄酒有限公司 | Equipment point-detecting method and device |
| CN109724791A (en) * | 2019-02-22 | 2019-05-07 | 朱清 | A kind of intelligence vibration analysis and trouble-shooter and its working method |
| CN110488841A (en) * | 2019-09-03 | 2019-11-22 | 国网湖南省电力有限公司 | Transformer equipment joint cruising inspection system and its application method based on intelligent robot |
| CN110749372A (en) * | 2018-07-18 | 2020-02-04 | 上海数深智能科技有限公司 | Motor vibration movement intelligent diagnosis system and use method thereof |
| CN110967474A (en) * | 2019-12-21 | 2020-04-07 | 广州新稳房屋安全鉴定有限公司 | Building strength detection method |
| CN111239253A (en) * | 2020-02-03 | 2020-06-05 | 浙江大学 | Detection method and application of aggregate elastic modulus |
-
2020
- 2020-08-19 CN CN202010838160.9A patent/CN111948295A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101226170A (en) * | 2007-12-26 | 2008-07-23 | 广东省建筑工程集团有限公司 | Method for detecting data aggregation judgment by foundation pile sound wave transmission method |
| CN101320018A (en) * | 2008-07-21 | 2008-12-10 | 哈尔滨工业大学 | Ultrasonic wave nondestructive apparatus and method for measuring residual stress of welded structure |
| CN101798957A (en) * | 2010-01-27 | 2010-08-11 | 北京信息科技大学 | Failure diagnosis method of power equipment |
| CN104596575A (en) * | 2014-12-25 | 2015-05-06 | 新疆新能钢结构有限责任公司 | Fan tower drum safe operation monitoring device and application method thereof |
| CN204615692U (en) * | 2015-05-12 | 2015-09-02 | 安徽理工大学 | Based on the supersonic motor measured operating parameter system of DSP |
| CN205404325U (en) * | 2016-02-17 | 2016-07-27 | 淮海工学院 | Indoor outstanding husky concentration calibration device |
| CN106124193A (en) * | 2016-05-30 | 2016-11-16 | 宁波诺丁汉大学 | Gearbox fault detection method in conjunction with vibrations with sound wave monitoring |
| CN108021064A (en) * | 2017-12-06 | 2018-05-11 | 合肥沙泰机电科技有限公司 | A kind of power-equipment health status inline diagnosis method |
| CN110749372A (en) * | 2018-07-18 | 2020-02-04 | 上海数深智能科技有限公司 | Motor vibration movement intelligent diagnosis system and use method thereof |
| CN109085811A (en) * | 2018-10-11 | 2018-12-25 | 中国长城葡萄酒有限公司 | Equipment point-detecting method and device |
| CN109724791A (en) * | 2019-02-22 | 2019-05-07 | 朱清 | A kind of intelligence vibration analysis and trouble-shooter and its working method |
| CN110488841A (en) * | 2019-09-03 | 2019-11-22 | 国网湖南省电力有限公司 | Transformer equipment joint cruising inspection system and its application method based on intelligent robot |
| CN110967474A (en) * | 2019-12-21 | 2020-04-07 | 广州新稳房屋安全鉴定有限公司 | Building strength detection method |
| CN111239253A (en) * | 2020-02-03 | 2020-06-05 | 浙江大学 | Detection method and application of aggregate elastic modulus |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114755611A (en) * | 2022-03-10 | 2022-07-15 | 重庆科创职业学院 | Sound wave-based detection method and device for turn-to-turn short circuit of oil-paper insulation transformer |
| CN115079042A (en) * | 2022-03-10 | 2022-09-20 | 重庆科创职业学院 | Sound wave-based transformer turn-to-turn short circuit detection and positioning method and device |
| CN115079042B (en) * | 2022-03-10 | 2023-06-06 | 重庆科创职业学院 | Acoustic wave-based transformer turn-to-turn short circuit detection positioning method and device |
| CN114755611B (en) * | 2022-03-10 | 2023-06-20 | 重庆科创职业学院 | Acoustic wave-based method and device for detecting turn-to-turn short circuit of oil paper insulation transformer |
| CN116125275A (en) * | 2023-04-04 | 2023-05-16 | 常州市美特精密电机有限公司 | Reducing motor test system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111948295A (en) | Fault detection system based on sound waves and motor fault detection method | |
| US8536839B2 (en) | Device and method for monitoring and/or analyzing rotors of electric machines in operation | |
| US20200174078A1 (en) | Vehicle battery maintenance device | |
| KR101846195B1 (en) | Motor status monitoring system and method thereof | |
| CN105511448A (en) | Integrated automotive diagnostic instrument and diagnosing method thereof | |
| CN111024416B (en) | Fault diagnosis method and system for train traction system | |
| CN116520093B (en) | High-voltage bus operation fault positioning method and device | |
| CN115327363B (en) | Method for carrying out live monitoring and state identification on mechanical characteristics of high-voltage circuit breaker | |
| KR102545672B1 (en) | Method and apparatus for machine fault diagnosis | |
| CN115655737A (en) | Health data acquisition and state judgment system for chassis dynamometer equipment | |
| CN107101742A (en) | A kind of vehicle connector monitoring device | |
| JP2006113668A (en) | Failure diagnosis device | |
| KR102544604B1 (en) | Method for detection of fault of synchronous machine | |
| CN107306213A (en) | Diagnostic method and diagnostic device for network | |
| CN112327213A (en) | Electric revolving body performance detection system and detection method | |
| CN111965259B (en) | Fault detection and inspection system based on sound waves | |
| CN220419514U (en) | On-line detection device for monitoring state of motor according to real-time temperature of motor | |
| CN114812378B (en) | Motor angle sensor mounting position and fault testing system and method | |
| CN108151795B (en) | Method and system for configuring a condition monitoring device | |
| CN116907565B (en) | System and method for detecting performance of rotary transformer sensor based on data analysis | |
| CN220653484U (en) | Manual and automatic inspection device for electric power data | |
| CN112684271A (en) | Method and device for detecting electrical equipment of tractor | |
| CN114217222A (en) | Method and system for monitoring running state of motor insulating bearing | |
| CN211855849U (en) | Vehicle failure detection device | |
| CN116819320A (en) | On-line detection device for monitoring state of motor according to real-time temperature of motor |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201117 |