CN114740352A - Non-contact motor fault detection method and system - Google Patents
Non-contact motor fault detection method and system Download PDFInfo
- Publication number
- CN114740352A CN114740352A CN202210645369.2A CN202210645369A CN114740352A CN 114740352 A CN114740352 A CN 114740352A CN 202210645369 A CN202210645369 A CN 202210645369A CN 114740352 A CN114740352 A CN 114740352A
- Authority
- CN
- China
- Prior art keywords
- motor
- characteristic value
- data
- abnormal
- contact
- 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
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/34—Testing dynamo-electric machines
- G01R31/343—Testing dynamo-electric machines in operation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
Abstract
The invention discloses a non-contact motor fault detection system, which comprises a noise sensor and a data processing module, wherein the noise sensor is used for sensing motor operation parameters of a motor to be detected in a non-contact mode; and the data processing module is used for judging whether the motor operating parameters are abnormal or not according to the characteristic value database and outputting motor fault information according to an abnormal result. The method comprises the steps of acquiring motor operation parameters in a non-contact mode, preprocessing the motor operation parameters, and establishing a motor operation characteristic curve representing motor full operation period data based on big data analysis; subsequently, whether the motor runs abnormally is identified by comparing the motor running characteristic curve with the motor running parameter deviation collected in real time on line, so that motor fault information is output with early warning performance; compared with the existing motor fault detection system, the system can realize non-contact signal acquisition, deep data mining processing and online fault detection; and has the advantages of less system equipment, simple implementation, convenient use and the like.
Description
Technical Field
The invention relates to the technical field of fault detection, in particular to a non-contact motor fault detection method and system.
Background
An electric motor is a transmission that converts electrical energy directly into mechanical energy without the need for any intermediate conversion mechanism. When the normal motor is in operation, the speed, current, temperature, vibration are all within the specified ranges. When the motor is abnormal or the load change is large, the motor can be blocked or out of step.
Existing automated measurement techniques for motor monitoring have long emerged and have experienced rapid development. The detection items aiming at the motor are comprehensive, such as the working current of the motor, vibration in XYZ directions, the current of the motor, the temperature of the motor, axial displacement, the rotating speed of the motor, acceleration and the like. The motor failure rate can be effectively reduced and the service life of the motor can be ensured through the real-time monitoring and analysis of the relevant parameters of the motor.
However, the common features of these motor monitoring systems are: on the electrical level, collecting signals from a motor or motor driving equipment (such as current); on the physical level, the acquisition sensor must be in mechanical contact with the motor or the motor connection device (e.g., a rotary speed encoder, a vibration sensor). Therefore, in the motor parameter detection of the practical application system of the motor (such as subway elevator, airport goods inspection, assembly line, etc.), the physical contact and signal transmission of the mechanical structure and the electric circuit are faced, and meanwhile, the safety risk of information interference of the original control system is faced.
Disclosure of Invention
The main purposes of the invention are as follows: the non-contact motor fault detection method and system are provided for solving the problems that an existing motor monitoring system faces physical contact and signal transmission of a mechanical structure and an electric circuit in motor parameter detection of an actual application system of a motor and faces safety risks of information interference of an original control system.
In order to achieve the above object, the present invention provides a non-contact motor fault detection system, which includes a noise sensor and a data processing module communicatively connected to the noise sensor, wherein the noise sensor is configured to sense a motor operating parameter of a motor to be detected in a non-contact manner, and the motor operating parameter includes motor operating state information and noise information; and the data processing module is used for judging whether the motor operating parameters are abnormal or not according to the characteristic value database and outputting motor fault information according to an abnormal result.
In the non-contact motor fault detection system provided by the invention, the data processing module comprises:
the characteristic value database is used for storing characteristic values representing normal operation of the motor;
the data preprocessing unit is used for preprocessing the motor operation parameters to generate a motor operation state characteristic value;
the data comparison unit is used for calculating a deviation value between the characteristic value of the motor running state and a corresponding characteristic value in the characteristic value database, judging that the motor running state is normal if the deviation value is smaller than a preset safety value, otherwise, judging that the motor running state is abnormal and outputting an abnormal result;
and the central processing unit is used for evaluating and outputting motor fault information according to the abnormal result and the motor abnormal database.
The non-contact motor fault detection system provided by the invention further comprises a big data analysis unit, wherein the big data analysis unit is used for establishing the characteristic value database representing the normal operation of the motor through data mining according to the collected motor full-period operation state data.
In the non-contact motor fault detection system provided by the present invention, the data preprocessing unit includes:
the filtering subunit is used for extracting the motor operation state information in the motor operation parameters;
and the fast Fourier transform subunit is used for carrying out Fourier transform on the motor running state information to generate frequency spectrum data, and generating the motor running state characteristic value according to the frequency spectrum data.
In addition, to achieve the above object, the present invention further provides a method for detecting a fault of a non-contact motor, including:
sensing motor operation parameters of a tested motor in a non-contact mode, wherein the motor operation parameters comprise motor operation state information and noise information; and
and judging whether the motor operation parameters are abnormal or not according to the characteristic value database, and outputting motor fault information according to an abnormal result.
The non-contact motor fault detection method provided by the invention comprises the following steps of judging whether the motor operation parameters are abnormal according to the characteristic value database, and outputting motor fault information according to an abnormal result:
preprocessing the motor operation parameters to generate a motor operation state characteristic value;
calculating deviation values between the characteristic values of the motor running state and the corresponding characteristic values in the characteristic value database;
judging whether the deviation value is smaller than a preset safety value, if so, judging that the running state of the motor is normal, otherwise, judging that the running state of the motor is abnormal and outputting an abnormal result; and
and evaluating and outputting motor fault information according to the abnormal result and the motor abnormal database.
The non-contact motor fault detection method provided by the invention further comprises the following steps:
collecting motor full-period running state data;
and establishing the characteristic value database representing the normal operation of the motor through data mining.
In the non-contact motor fault detection method provided by the invention, the step of preprocessing the motor operation parameters and generating the motor operation state characteristic value comprises the following steps:
extracting the motor running state information in the motor running parameters;
carrying out Fourier transform on the motor running state information to generate frequency spectrum data; and
and generating the characteristic value of the running state of the motor according to the frequency spectrum data.
The invention also provides a computer readable storage medium, in which a computer program is stored, which computer program, when being executed by a processor, realizes the steps of the non-contact motor fault detection method as described above.
The non-contact motor fault detection system and method provided by the invention have the following beneficial effects: the method comprises the steps of acquiring motor operation parameters in a non-contact mode, preprocessing the motor operation parameters, and establishing a motor operation characteristic curve representing motor full operation period data based on big data analysis; subsequently, whether the motor runs abnormally is identified by comparing the motor running characteristic curve with the motor running parameter deviation collected in real time on line, so that motor fault information is output with early warning performance; therefore, compared with the existing motor fault detection system, the system can realize non-contact signal acquisition, data deep mining processing and online fault detection; and has the advantages of less system equipment, simple implementation, convenient use and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts:
fig. 1 is a schematic diagram of a non-contact motor fault detection system according to an embodiment of the present invention;
fig. 2 is a schematic diagram of the data processing module shown in fig. 1.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Exemplary embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
The general idea of the invention is as follows: aiming at the problem that the existing motor monitoring system faces physical contact and signal transmission of a mechanical structure and an electric circuit and faces a safety risk of information interference of an original control system in the motor parameter detection of a practical application system of a motor, the motor operation parameters are obtained in a non-contact mode, and after pretreatment, a motor operation characteristic curve representing the full operation period data of the motor is established based on big data analysis; and subsequently, whether the motor operates abnormally is identified by comparing the motor operation characteristic curve with the motor operation parameter deviation acquired in real time on line, so that early warning is achieved and motor fault information is output. Therefore, compared with the existing motor fault detection system, the system can realize non-contact signal acquisition, data deep mining processing and online fault detection; and has the advantages of less system equipment, simple implementation, convenient use and the like.
In order to better understand the technical solutions, the technical solutions will be described in detail below with reference to the drawings and the specific embodiments of the specification, and it should be understood that the embodiments and specific features of the embodiments of the present invention are detailed descriptions of the technical solutions of the present application, and are not limited to the technical solutions of the present application, and the technical features of the embodiments and examples of the present invention may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic diagram of a non-contact motor fault detection system according to an embodiment of the present invention. In the present embodiment, the non-contact motor fault detection system 10 is used for monitoring the operation state of the motor 20 under test, and includes a noise sensor 110 and a data processing module 120 communicatively connected to the noise sensor 100, wherein data transmission is performed between the noise sensor 110 and the data processing module 120 in a wired or wireless manner.
Specifically, in an embodiment of the present invention, the noise sensor 110 is configured to sense the motor operating parameters of the measured motor 20 in a non-contact manner, wherein the motor operating parameters include motor operating state information and noise information. Current non-contact detection methods include magnetic induction detection and light induction detection. The magnetic induction detection has the characteristic of coupling action of an excitation end (such as a primary coil of a transformer) and an induction end (such as a secondary coil of the transformer), the working principle of the motor is electromagnetic induction-mechanical rotation, and in order to shield the influence of an external magnetic field on the operation of the motor, a magnetic shielding metal shell is additionally arranged during the manufacturing of the motor, so that the condition of the motor is represented by means of the magnetic induction detection, which is unrealistic and lacks information. The light sensing detection generally requires emitting a measuring beam (e.g., laser) to a detection target device, collecting a detecting beam reflected by the target device, and extracting a vibration signal from the detecting beam. For motor detection: a first desired excitation beam; secondly, the excitation and detection light path is smooth and has no obstruction; thirdly, whether the extracted vibration signal can represent the running characteristics of the motor or not. Therefore, neither of these non-contact detection methods is suitable for motor detection. Therefore, in the present invention, by detecting the motor operation noise, the noise can represent the motor operation state. Compared with the detection mode, the noise is generated by the operation of the motor, and the detection only needs induction without an excitation source; the noise sensor is only used for one-way and inductive receiving, and the operation of the motor is not influenced; as long as the noise sensor is in the detection sensitivity range, the requirements on the installation position and the distance are not required; the noise sound wave has transmission and diffraction characteristics (at the low end of the frequency spectrum), and the existence of shielding between the noise sensor and the motor is not required to be considered; the noise sensor has high cost performance and lower cost in the aspects of equipment composition, installation and use. Therefore, the noise sensor is used for detecting noise to obtain the motor operation parameters without an excitation source, shielding is not feared, and the arrangement is flexible and convenient.
Specifically, in an embodiment of the present invention, the data processing module 120 is configured to determine whether the motor operating parameter is abnormal according to a characteristic value database, and output motor fault information according to an abnormal result. After acquiring the motor operating parameters in a non-contact manner that does not generate an interference risk to the original motor system, the acquired data needs to be processed, and the feature data obtained by the processing is compared and determined, so as to be shown in fig. 2, the data processing module 120 includes: the data preprocessing unit 1201 is used for preprocessing the motor operation parameters to generate a motor operation state characteristic value; a data comparison unit 1202, configured to calculate a deviation value between the characteristic value of the motor operating state and a corresponding characteristic value in the characteristic value database, and if the deviation value is smaller than a preset safety value, determine that the motor operating state is normal, otherwise, determine that the motor operating state is abnormal and output an abnormal result; a characteristic value database 1203, configured to store characteristic values representing normal operations of the motor; the central processing unit 1204 is used for evaluating and outputting motor fault information according to the abnormal result and the motor abnormal database; and the big data analysis unit 1205 is used for establishing the characteristic value database representing normal operation of the motor through data mining according to the acquired motor full-period operation state data.
Further, in an embodiment of the present invention, the data collected by the noise sensor for detecting the operating state of the motor includes not only information representing the operating state of the motor, but also background noise acting continuously and periodically, such as noise generated by resonance of environment and mechanical components, so that the operating parameters of the motor obtained by the noise sensor include information of the operating state of the motor and noise information, and therefore, the data preprocessing unit 1201 includes: a filtering subunit 12011, configured to extract the motor operation state information in the motor operation parameter; and the fast fourier transform subunit 12012 is configured to perform fourier transform on the motor operation state information, generate frequency spectrum data, and generate a characteristic value of the motor operation state according to the frequency spectrum data.
Furthermore, the traditional filter has a high-pass filter, a low-pass filter and a band-pass (blocking) filter, and cannot be applied to background noise processing, so that the method selects the Kalman filter to realize real-time identification of background noise textural features, realizes extraction of background noise frequency band distribution and bandwidth, and achieves the aim of realizing signal-noise separation. The basic idea of Kalman filtering is as follows: and updating the estimation of the state variable by using the estimation value of the previous moment and the observation value of the current moment by using a state space model of the signal and the noise, and calculating the estimation value of the current moment. It is suitable for real-time processing and computer operation. Kalman filtering is an optimized autoregressive data processing algorithm, does not require both signal and noise to be stationary processes, and for system disturbances and observation errors (i.e., noise) at each time, by processing the observation signals containing noise, it is possible to obtain an estimate of the true signal with the smallest error in the sense of averaging, provided that some appropriate assumptions are made about their statistical properties. Kalman filtering is a new linear filtering and predicting theory, which recurs in the order of 'prediction-actual measurement-correction' to process noisy input and observed signals and obtain the real signal of the system.
Further, the motor running state signal obtained through Kalman filtering is a time domain signal in essence, and the signal amplitude of the time domain signal is insufficient or uniquely represents the current motor running state. By performing FFT to generate spectrum data and then intelligently searching for peaks in the spectrum, a characteristic value (spectrum band) representing the maximum correlation with the motor operating state is obtained by tracking the frequency of a key component in the spectrum.
Further, in an embodiment of the present invention, the characteristic value database 1202 stores characteristic value data of the motor operation in a database structure, and is accessed by the data comparing unit.
Further, in an embodiment of the present invention, the data comparing unit 1203 receives the characteristic value of the motor running state in real time, and compares the characteristic value with the corresponding characteristic data in the characteristic database, and if the deviation value of the real-time characteristic value is within the preset safety value range, it is determined that the motor running state is normal; otherwise, the motor running state is determined to be abnormal; and marking abnormal information, and outputting and transmitting an abnormal result to the central processing unit.
Further, in one embodiment of the invention, the central processing unit 1204 manages the execution of the call to the above-mentioned units and the subsequent processing of the results. And (3) for the abnormal information marked by the data comparison unit, a motor abnormal database is constructed by adopting data statistics, regression analysis, variance analysis, clustering analysis and other data deep processing methods, and the motor fault information is estimated and output by combining the current abnormal result and the historical data.
Further, in an embodiment of the present invention, the big data analysis unit 1205 uses the motor full-period operation state data collected by the noise sensor, and obtains the characteristic value representing the correlation with the motor operation state through the analysis of the data preprocessing unit, and the big data processing process based on the data mining of various algorithms (more typical algorithms include K-Means for clustering, SVM for statistical learning, and Naive Bayes for classification, and mainly used tools include Mahout of Hadoop); and establishing a characteristic value database for representing the operation of the motor by a partial least square method and other similar algorithm constructions.
Correspondingly, the invention also provides a non-contact motor fault detection method, which comprises the following steps:
s1, sensing motor operation parameters of the detected motor in a non-contact mode, wherein the motor operation parameters comprise motor operation state information and noise information; and
and S2, judging whether the motor operation parameters are abnormal or not according to the characteristic value database, and outputting motor fault information according to an abnormal result.
Specifically, in an embodiment of the present invention, the motor operation parameter of the motor under test is sensed by the noise sensor in a non-contact manner. The noise sensor is used for detecting noise to obtain the running parameters of the motor without an excitation source, and the device is free of fear and shielding and flexible and convenient to arrange.
Specifically, in an embodiment of the present invention, after the motor operation parameters are collected in a non-contact manner that does not generate an interference risk to the original motor system, the obtained data needs to be processed, and the feature data obtained by the processing needs to be compared and determined. Therefore, step S2 includes:
s21, preprocessing the motor operation parameters to generate a motor operation state characteristic value;
s22, calculating a deviation value between the characteristic value of the motor running state and the corresponding characteristic value in the characteristic value database;
s23, judging whether the deviation value is smaller than a preset safety value, if so, judging that the running state of the motor is normal, otherwise, judging that the running state of the motor is abnormal and outputting an abnormal result; and
and S24, evaluating and outputting motor fault information according to the abnormal result and the motor abnormal database.
Further, in an embodiment of the present invention, the data collected by the noise sensor for detecting the operating state of the motor includes not only information representing the operating state of the motor, but also background noise acting continuously and periodically, such as noise generated by resonance of environment and mechanical components, so that step S21 includes:
s211, extracting the motor running state information in the motor running parameters;
s212, carrying out Fourier transform on the motor running state information to generate frequency spectrum data; and
and S213, generating the characteristic value of the motor running state according to the frequency spectrum data.
Furthermore, the traditional filter has a high-pass filter, a low-pass filter and a band-pass (blocking) filter, and cannot be applied to background noise processing, so that the method selects the Kalman filter to realize real-time identification of background noise textural features, realizes extraction of background noise frequency band distribution and bandwidth, and achieves the aim of realizing signal-noise separation.
Further, the motor running state signal obtained through Kalman filtering is a time domain signal in essence, and the signal amplitude of the time domain signal is insufficient or uniquely represents the current motor running state. By performing FFT to generate spectrum data and then intelligently searching for peaks in the spectrum, a characteristic value (spectrum band) representing the maximum correlation with the motor operating state is obtained by tracking the frequency of a key component in the spectrum.
Further, in an embodiment of the present invention, the motor full-period operation state data acquired by the noise sensor is also used, and a feature value representing the correlation with the motor operation state is obtained through preprocessing and analysis, and a big data processing process based on data mining of various algorithms is performed (typical algorithms include K-Means for clustering, SVM for statistical learning, and Naive Bayes for classification, and tools mainly used include Mahout of Hadoop); and establishing a characteristic value database for representing the operation of the motor by using a partial least square method and other similar algorithm constructions. Therefore, the method further comprises the following steps: collecting motor full-period running state data; and establishing the characteristic value database representing the normal operation of the motor through data mining.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (9)
1. The non-contact motor fault detection system is characterized by comprising a noise sensor and a data processing module which is in communication connection with the noise sensor, wherein the noise sensor is used for sensing motor operation parameters of a motor to be detected in a non-contact mode, and the motor operation parameters comprise motor operation state information and noise information; and the data processing module is used for judging whether the motor operating parameters are abnormal or not according to the characteristic value database and outputting motor fault information according to an abnormal result.
2. The non-contact motor fault detection system of claim 1, wherein said data processing module comprises:
the characteristic value database is used for storing characteristic values representing normal operation of the motor;
the data preprocessing unit is used for preprocessing the motor operation parameters to generate a motor operation state characteristic value;
the data comparison unit is used for calculating a deviation value between the characteristic value of the motor running state and a corresponding characteristic value in the characteristic value database, judging that the motor running state is normal if the deviation value is smaller than a preset safety value, otherwise, judging that the motor running state is abnormal and outputting an abnormal result;
and the central processing unit is used for evaluating and outputting motor fault information according to the abnormal result and the motor abnormal database.
3. The non-contact motor fault detection system of claim 2, further comprising a big data analysis unit for establishing said characteristic value database characterizing normal operation of the motor by data mining based on collected full-cycle operating state data of the motor.
4. The non-contact motor failure detection system of claim 2, wherein said data preprocessing unit comprises:
the filtering subunit is used for extracting the motor operation state information in the motor operation parameters;
and the fast Fourier transform subunit is used for carrying out Fourier transform on the motor running state information to generate frequency spectrum data, and generating the motor running state characteristic value according to the frequency spectrum data.
5. A non-contact motor fault detection method is characterized by comprising the following steps:
sensing motor operation parameters of a tested motor in a non-contact mode, wherein the motor operation parameters comprise motor operation state information and noise information; and
and judging whether the motor operation parameters are abnormal or not according to the characteristic value database, and outputting motor fault information according to an abnormal result.
6. The non-contact motor fault detection method of claim 5, wherein the step of judging whether the motor operation parameter is abnormal according to the characteristic value database and outputting motor fault information according to the abnormal result comprises:
preprocessing the motor operation parameters to generate a motor operation state characteristic value;
calculating deviation values between the characteristic values of the motor running state and the corresponding characteristic values in the characteristic value database;
judging whether the deviation value is smaller than a preset safety value, if so, judging that the running state of the motor is normal, otherwise, judging that the running state of the motor is abnormal and outputting an abnormal result; and
and evaluating and outputting motor fault information according to the abnormal result and the motor abnormal database.
7. The non-contact motor fault detection method of claim 6, further comprising:
collecting motor full-period running state data;
and establishing the characteristic value database representing the normal operation of the motor through data mining.
8. The non-contact motor fault detection method of claim 6, wherein the step of preprocessing the motor operating parameters to generate motor operating condition characteristic values comprises:
extracting the motor running state information in the motor running parameters;
carrying out Fourier transform on the motor running state information to generate frequency spectrum data; and
and generating the characteristic value of the running state of the motor according to the frequency spectrum data.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when being executed by a processor, carries out the steps of the contactless motor fault detection method according to any one of claims 5 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210645369.2A CN114740352A (en) | 2022-06-09 | 2022-06-09 | Non-contact motor fault detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210645369.2A CN114740352A (en) | 2022-06-09 | 2022-06-09 | Non-contact motor fault detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114740352A true CN114740352A (en) | 2022-07-12 |
Family
ID=82286694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210645369.2A Pending CN114740352A (en) | 2022-06-09 | 2022-06-09 | Non-contact motor fault detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114740352A (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1884990A (en) * | 2006-07-04 | 2006-12-27 | 清华大学深圳研究生院 | Vibrating detection method for detecting looseness of large-scale generator rotor slot wedge and apparatus therefor |
| CN202329691U (en) * | 2011-12-05 | 2012-07-11 | 山东建筑大学 | Remote monitoring system for communication base station electricity generators |
| CN103698699A (en) * | 2013-12-06 | 2014-04-02 | 西安交通大学 | Asynchronous motor fault monitoring and diagnosing method based on model |
| CN103733080A (en) * | 2011-08-01 | 2014-04-16 | 维也纳技术大学 | Method and device for detecting a deterioration in the state of an insulation in an operating electric machine |
| CN107609574A (en) * | 2017-08-18 | 2018-01-19 | 上海电力学院 | Wind turbines fault early warning method based on data mining |
| CN107797063A (en) * | 2017-09-19 | 2018-03-13 | 北京瑞盈同创智能技术研究院有限公司 | Running of wind generating set state estimation and method for diagnosing faults based on SCADA |
| CN108152736A (en) * | 2017-12-07 | 2018-06-12 | 上海大学 | Utilize electric system parameter monitoring load variation and the autonomous sensory perceptual system of system exception |
| CN110492497A (en) * | 2019-08-16 | 2019-11-22 | 国网河南省电力公司电力科学研究院 | A kind of generating set power oscillation error comprehensive diagnosis method and system |
| CN110542858A (en) * | 2019-09-24 | 2019-12-06 | 中国矿业大学 | Non-invasive asynchronous motor rotor initial fault detection method |
| CN210180536U (en) * | 2019-08-07 | 2020-03-24 | 浙江德欧电气技术有限公司 | Double-motor coaxial coupling cross-reference steady-state noise detection device |
| CN111695618A (en) * | 2020-06-01 | 2020-09-22 | 清华大学深圳国际研究生院 | Electric vehicle motor fault detection method based on OBD data |
| CN111693865A (en) * | 2020-06-18 | 2020-09-22 | 上海电气集团上海电机厂有限公司 | Motor cluster electromagnetic wave remote detection device and method based on SDR technology |
| CN112052796A (en) * | 2020-09-07 | 2020-12-08 | 电子科技大学 | Permanent magnet synchronous motor fault diagnosis method based on deep learning |
| CN213149750U (en) * | 2020-09-04 | 2021-05-07 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | State evaluation and fault prediction system for steam turbine generator unit |
| CN112834224A (en) * | 2021-01-05 | 2021-05-25 | 广东核电合营有限公司 | Method and system for evaluating health state of nuclear power steam turbine generator |
| CN114035047A (en) * | 2021-11-22 | 2022-02-11 | 安徽理工大学 | Mine ventilation machine motor fault early warning device based on audio frequency identification |
| CN216144922U (en) * | 2021-06-16 | 2022-03-29 | 苏州捷杰传感技术有限公司 | Motor state monitoring sensor and system |
| CN114374347A (en) * | 2022-01-17 | 2022-04-19 | 上海大学 | Dual-controller motor control system monitoring software deployment method and system |
-
2022
- 2022-06-09 CN CN202210645369.2A patent/CN114740352A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1884990A (en) * | 2006-07-04 | 2006-12-27 | 清华大学深圳研究生院 | Vibrating detection method for detecting looseness of large-scale generator rotor slot wedge and apparatus therefor |
| CN103733080A (en) * | 2011-08-01 | 2014-04-16 | 维也纳技术大学 | Method and device for detecting a deterioration in the state of an insulation in an operating electric machine |
| CN202329691U (en) * | 2011-12-05 | 2012-07-11 | 山东建筑大学 | Remote monitoring system for communication base station electricity generators |
| CN103698699A (en) * | 2013-12-06 | 2014-04-02 | 西安交通大学 | Asynchronous motor fault monitoring and diagnosing method based on model |
| CN107609574A (en) * | 2017-08-18 | 2018-01-19 | 上海电力学院 | Wind turbines fault early warning method based on data mining |
| CN107797063A (en) * | 2017-09-19 | 2018-03-13 | 北京瑞盈同创智能技术研究院有限公司 | Running of wind generating set state estimation and method for diagnosing faults based on SCADA |
| CN108152736A (en) * | 2017-12-07 | 2018-06-12 | 上海大学 | Utilize electric system parameter monitoring load variation and the autonomous sensory perceptual system of system exception |
| CN210180536U (en) * | 2019-08-07 | 2020-03-24 | 浙江德欧电气技术有限公司 | Double-motor coaxial coupling cross-reference steady-state noise detection device |
| CN110492497A (en) * | 2019-08-16 | 2019-11-22 | 国网河南省电力公司电力科学研究院 | A kind of generating set power oscillation error comprehensive diagnosis method and system |
| CN110542858A (en) * | 2019-09-24 | 2019-12-06 | 中国矿业大学 | Non-invasive asynchronous motor rotor initial fault detection method |
| CN111695618A (en) * | 2020-06-01 | 2020-09-22 | 清华大学深圳国际研究生院 | Electric vehicle motor fault detection method based on OBD data |
| CN111693865A (en) * | 2020-06-18 | 2020-09-22 | 上海电气集团上海电机厂有限公司 | Motor cluster electromagnetic wave remote detection device and method based on SDR technology |
| CN213149750U (en) * | 2020-09-04 | 2021-05-07 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | State evaluation and fault prediction system for steam turbine generator unit |
| CN112052796A (en) * | 2020-09-07 | 2020-12-08 | 电子科技大学 | Permanent magnet synchronous motor fault diagnosis method based on deep learning |
| CN112834224A (en) * | 2021-01-05 | 2021-05-25 | 广东核电合营有限公司 | Method and system for evaluating health state of nuclear power steam turbine generator |
| CN216144922U (en) * | 2021-06-16 | 2022-03-29 | 苏州捷杰传感技术有限公司 | Motor state monitoring sensor and system |
| CN114035047A (en) * | 2021-11-22 | 2022-02-11 | 安徽理工大学 | Mine ventilation machine motor fault early warning device based on audio frequency identification |
| CN114374347A (en) * | 2022-01-17 | 2022-04-19 | 上海大学 | Dual-controller motor control system monitoring software deployment method and system |
Non-Patent Citations (4)
| Title |
|---|
| 喻伟 等: "基于CEEMD和小波包变换的重力数据信噪分离方法", 《软件》 * |
| 喻伟 等: "基于瞬时混合模型的独立分量分析重力数据信噪分离方法", 《重力测量技术——2014年惯性技术发展动态发展方向研讨会文集》 * |
| 李岩松 等: "基于序贯卡尔曼滤波的OCT信号处理方法研究", 《电测与仪表》 * |
| 杨柏: "基于改进卷积神经网络永磁电机故障诊断方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wen et al. | Graph modeling of singular values for early fault detection and diagnosis of rolling element bearings | |
| CN111259990B (en) | Seawater pump fault monitoring device and diagnosis method based on multi-source information fusion | |
| US20150233792A1 (en) | Methods and Apparatuses for Defect Diagnosis in a Mechanical System | |
| CN113748326B (en) | Method for estimating bearing fault severity for induction motor | |
| CN111967338B (en) | Method and system for judging partial discharge pulse interference signals based on mean shift clustering algorithm | |
| Chegini et al. | New fault diagnosis approaches for detecting the bearing slight degradation | |
| KR102301201B1 (en) | Apparatus and method for precise state diagnosis of rotating machinery based on IoT sensor | |
| Liu et al. | Technology development and commercial applications of industrial fault diagnosis system: a review | |
| CN107782551A (en) | A kind of appraisal procedure of mechanical part degree of injury | |
| Shi et al. | The VMD-scale space based hoyergram and its application in rolling bearing fault diagnosis | |
| CN110186384B (en) | Ship structure stress monitoring system sensor deviation fault diagnosis method | |
| CN105445004B (en) | Method is predicted in the oscillating curve normalization average life span of equipment component | |
| KR102374980B1 (en) | Multi-Sensor Based Artificial Intelligent Fault Diagnosis System Of Mechanical Device | |
| CN116953395B (en) | Method, device, equipment and storage medium for detecting electricity stealing of charging pile | |
| CN114740352A (en) | Non-contact motor fault detection method and system | |
| CN112380782A (en) | Rotating equipment fault prediction method based on mixed indexes and neural network | |
| CN117076869A (en) | Time-frequency domain fusion fault diagnosis method and system for rotary machine | |
| CN117435908A (en) | Multi-fault feature extraction method for rotary machine | |
| CN112486722A (en) | System fault detection method and related device | |
| US20230024104A1 (en) | Identification of false transformer humming using machine learning | |
| Yaqub et al. | Machine fault severity estimation based on adaptive wavelet nodes selection and SVM | |
| JP2020187955A (en) | Method and device for diagnosing switchgear | |
| CN116434368A (en) | Multifunctional handheld inspection instrument and inspection method | |
| Yao et al. | A framework via impulses-oriented Gini index and extreme value distribution for rolling bearing dynamic fault alarm and identification | |
| Talmoudi et al. | Tracking and Visualizing Signs of Degradation for Early Failure Prediction of Rolling Bearings |
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: 20220712 |