CN108152738B - Motor working condition monitoring method and device - Google Patents
Motor working condition monitoring method and device Download PDFInfo
- Publication number
- CN108152738B CN108152738B CN201711425098.5A CN201711425098A CN108152738B CN 108152738 B CN108152738 B CN 108152738B CN 201711425098 A CN201711425098 A CN 201711425098A CN 108152738 B CN108152738 B CN 108152738B
- Authority
- CN
- China
- Prior art keywords
- motor
- current digital
- digital signals
- working current
- motor working
- 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.)
- Active
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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Electric Motors In General (AREA)
- Tests Of Circuit Breakers, Generators, And Electric Motors (AREA)
Abstract
The invention discloses a method and a device for monitoring the working condition of an electric machine, wherein the method comprises the following steps: collecting the working current of a motor; performing AD conversion on the collected motor working current to obtain a motor working current digital signal; classifying and storing the motor working current digital signals according to a preset classification rule; extracting a plurality of motor working current digital signals from the storage content at a preset period aiming at each class of motor working current digital signals after classified storage; taking the classification category of the currently extracted motor working current digital signals as a condition, and obtaining a motor working condition diagnosis result based on the variation trend of the extracted plurality of motor working current digital signals; the invention can identify whether the motor is abnormal or not in advance, and start early warning before the motor is not aged enough to trigger the warning signal.
Description
Technical Field
The invention relates to the technical field of motor working condition monitoring, in particular to a motor working condition monitoring method and a motor working condition monitoring device.
Background
Self-service transaction equipment such as an ATM (automatic teller machine), a cash recycling all-in-one machine, a cash dispensing all-in-one machine, a self-service financial device and the like usually needs to adopt a certain number of various motors to provide power for a machine core transmission and a cash dispensing mechanism, and the like. In the prior art, as for the working condition monitoring means of the motors, functional signals of overcurrent, overtemperature, coil open circuit and the like carried by the motor driver are basically read, when mechanical transmission load is increased, the working current of the motor and the motor driver is increased, the temperature is also increased, once the working current exceeds an original upper limit value, an alarm signal is further triggered, and the system is immediately stopped or reports an error.
The device can be immediately protected from being damaged by the motor working condition monitoring means, but under the condition that the current of a mechanical transmission load is slowly increased due to gear belt abrasion or grease dryness and the like, the system is unknown as long as the current does not exceed the original upper limit value; over time, such abnormal wear of the machine and the high current operation of the motor and the device will continue to occur, which in turn will accelerate the aging of the machine, the motor and the device, and the power consumption will further increase.
Disclosure of Invention
Aiming at the problems, the invention provides a method and a device for monitoring the working condition of the motor, which can effectively know the working condition of the motor and is beneficial to prolonging the service life of the motor.
The technical means of the invention are as follows:
a method for monitoring the working condition of an electric machine comprises the following steps:
collecting the working current of a motor;
performing AD conversion on the collected motor working current to obtain a motor working current digital signal;
classifying and storing the motor working current digital signals according to a preset classification rule;
extracting a plurality of motor working current digital signals from the storage content at a preset period aiming at each class of motor working current digital signals after classified storage;
taking the classification category of the currently extracted motor working current digital signals as a condition, and obtaining a motor working condition diagnosis result based on the variation trend of the extracted plurality of motor working current digital signals;
further, the step of outputting the motor working condition diagnosis result based on the variation trend of the extracted plurality of motor working current digital signals by using the classification category of the currently extracted motor working current digital signal as a condition specifically includes:
determining the motor working current digital signals belonging to abnormal data points based on the variation trend of the extracted plurality of motor working current digital signals by taking the classification category of the currently extracted motor working current digital signals as a condition;
taking a plurality of different abnormal data points as sample data, and adding labels of corresponding motor working condition diagnosis results to the sample data;
performing machine learning training on the sample data and establishing a machine learning model, wherein the machine learning model is used for outputting a motor working condition diagnosis result under the condition that a plurality of motor working current digital signals in a preset period are input;
further, the preset classification rule is a motor type, a motor index number, a motor function, a motor working state and/or a motor service mode;
further, the preset period is set according to different working time lengths of the motor;
further, adding a corresponding motor working condition diagnosis result label for the sample data, and simultaneously adding a processing opinion label for the sample data; and the machine learning model outputs a corresponding processing suggestion while outputting a motor working condition diagnosis result.
An electric machine condition monitoring device comprising:
a collecting part configured to collect a motor operating current;
an A/D conversion part configured to perform AD conversion on the collected motor working current to obtain a motor working current digital signal;
a storage section configured to store the motor operating current digital signals in a classified manner according to a preset classification rule;
an extracting section configured to extract a plurality of motor operating current digital signals from the stored contents at a predetermined cycle for each class of motor operating current digital signals after the classification storage; and
a processing part configured to obtain a motor working condition diagnosis result based on a variation trend of the extracted plurality of motor working current digital signals with a classification category of the currently extracted motor working current digital signals as a condition;
further, the processing section is specifically configured to perform the following operations:
determining the motor working current digital signals belonging to abnormal data points based on the variation trend of the extracted plurality of motor working current digital signals by taking the classification category of the currently extracted motor working current digital signals as a condition;
taking a plurality of different abnormal data points as sample data, and adding labels of corresponding motor working condition diagnosis results to the sample data;
performing machine learning training on the sample data and establishing a machine learning model, wherein the machine learning model is used for outputting a motor working condition diagnosis result under the condition that a plurality of motor working current digital signals in a preset period are input;
the method is further characterized in that the preset classification rule is a motor type, a motor index number, a motor function, a motor working state and/or a motor service mode;
further, the preset period is set according to different working time lengths of the motor;
further, when a corresponding motor working condition diagnosis result label is added to the sample data, the processing part also adds a processing opinion label to the sample data; and the machine learning model outputs a corresponding processing suggestion while outputting a motor working condition diagnosis result.
By adopting the technical scheme, the method and the device for monitoring the working condition of the motor can realize the periodic analysis of the change trend of the working current of the motor, can identify whether the motor operates abnormally or not in advance by combining a machine learning mode, can start early warning before the motor fails and is aged to be insufficient to trigger an alarm signal so as to guide and arrange a maintainer to overhaul or shut down the motor in time, can prevent the self-service financial equipment from being further damaged due to the problem of the motor, so that an equipment manager can visually know the operating state of the motor according to the motor, replace the motor in time and improve the operating efficiency of the self-service financial equipment.
Drawings
FIG. 1 is a flow chart of a motor condition monitoring method according to embodiment 1 of the present invention;
FIG. 2 is a flowchart showing an example of the process of step 5 in example 1 of the present invention;
fig. 3 is a block diagram of a motor condition monitoring apparatus according to embodiment 1 of the present invention;
fig. 4 is a driving example diagram of a dc brushless motor according to the present invention;
FIG. 5 is a driving example diagram of a DC brush motor according to the present invention;
fig. 6 is a driving example diagram of a stepping motor according to the present invention;
fig. 7 is a diagram showing an example of AD conversion of the present invention.
Detailed Description
In order to make the objects, technical solutions and technical effects of the present invention more clear, the present invention is further described in detail below with reference to the accompanying drawings and the detailed description. It should be understood that the detailed description and specific examples, while indicating the preferred embodiment of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention. The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
The invention provides a method for monitoring the working condition of a motor, and fig. 1 is a flow chart of the method for monitoring the working condition of the motor in embodiment 1 of the invention, as shown in fig. 1, the method can comprise the following steps:
step 1: collecting the working current of a motor; the collection of the working current of the motor can adopt real-time sampling or time-sharing sampling;
step 2: performing AD conversion on the collected motor working current to obtain a motor working current digital signal; assuming that the motor condition monitoring method described in this embodiment is applied to automatic transaction devices, self-service financial equipment, and the like, the types of motors involved in these devices or equipment may be a stepping motor, a direct current brush motor, a direct current brushless motor, a servo motor, and the like; fig. 4 illustrates an example of driving a dc brushless motor according to the present invention, as shown in fig. 4, the dc brushless motor may be driven by a motor driving chip of type a4938, a motor operating current may be collected by a pin SENSE of a4938, specifically, a sampling resistor Rs Is 0.03 Ω, a current Is flowing through the sampling resistor Is 0-6A, and a sampling voltage Vs Is 0-0.18V, and further, the motor operating current may be amplified by an amplification factor n of 10 before AD conversion Is performed on the motor operating current; fig. 5 shows an example of driving the dc brush motor according to the present invention, as shown in fig. 5, the dc brush motor may be driven by a motor driving chip of DRV8800, the motor working current may be collected by a pin SENSE of DRV8800, specifically, a sampling resistor Rs Is 0.1 Ω, a current Is flowing through the sampling resistor Is 0-1A, and a sampling voltage Vs Is 0-0.1V, and further, the motor working current may be amplified by an amplification factor n of 20 before AD conversion Is performed on the motor working current; fig. 6 shows an example of driving a stepping motor according to the present invention, as shown in fig. 6, the stepping motor may be driven by a motor driving chip of the model SLA7078MS, a motor operating current may be collected by pins SenseA and SenseB of SLA7078MS, specifically, a sampling resistor Rs Is 0.155 Ω Is built in SLA7078MS, a current Is flowing through the sampling resistor Is 0-3A, and a sampling voltage Vs Is 0-0.465V, and further, before AD conversion Is performed on the motor operating current, the motor operating current may be amplified by an amplification factor n-5; fig. 7 shows an example of AD conversion according to the present invention, where M1, M2, … …, Mn in fig. 7 may refer to collected motor operating currents, the ADC chip in fig. 7 Is used to implement AD conversion on the collected motor operating currents, the sampling resolution of the ADC chip may be 12 bits, the voltage of the pin Vref of the ADC chip Is directly represented by Vref, and the motor operating current Is ═ Vs/Rs ═ ((ADC/4098): Vref)/(Rs × n), where ADC represents the sampling resolution of the ADC chip, Vref represents the voltage of the pin Vref of the ADC chip, Rs represents the size of the sampling resistor, and n represents the aforementioned amplification factor; the ADC chip can select a general ADC device with multi-channel analog input and 10-bit or more parallel digital signal output, and the requirement on real-time performance is not high, so that the requirement on low-frequency sampling clock ADC can be met.
And step 3: classifying and storing the motor working current digital signals according to a preset classification rule; the preset classification rule can be set in advance, and preferably, the preset classification rule can be a motor type, a motor index number, a motor function, a motor working state and/or a motor service mode; the motor type can be a stepping motor, a direct current brush motor, a direct current brushless motor, a servo motor and the like; the motor index number can be M0001, M0002, M0003 and the like; the motor can be used for transmitting power through a channel, digging and dividing paper money power, lifting and pushing power and the like; the working state of the motor can be starting, continuous operation, no load, load and the like; the motor business mode can be testing, withdrawing money, depositing, clearing and the like; each of the above categories may be used as a motor condition, for example, a motor condition diagnosis result with the motor type being a stepping motor may be output according to a variation trend of a plurality of extracted motor operating current digital signals with the motor type being the stepping motor, a motor condition diagnosis result with the motor index number being M0001 may be output according to a variation trend of a plurality of extracted motor operating current digital signals with the motor index number being M0001, a motor condition diagnosis result with the motor function being a channel transmission power may be output according to a variation trend of a plurality of extracted motor operating current digital signals with the motor function being a channel transmission power, or a motor condition diagnosis result with the motor operating state being a loaded motor condition may be output according to a variation trend of a plurality of extracted motor operating current digital signals with the motor function being a channel transmission power, the motor working condition diagnosis result with the motor service mode being the score can be output according to the variation trend of the extracted motor working current digital signals with the motor service mode being the score, namely the classification category of the currently extracted motor working current digital signals can be a specific motor type, a motor index number, a motor function, a motor working state and/or a motor service mode; the actual process of classifying and storing the motor working current digital signals can be that the motor working current digital signals of the same classification category are moved into respective box-type stacks, further, the single stack is full and can correspond to the motor working current change under a single working condition, a plurality of stacks can correspond to the motor working current change under a plurality of working conditions, the single stack can correspond to the working condition state of a single motor, and a plurality of stacks can correspond to the working condition states of a plurality of motors.
And 4, step 4: extracting a plurality of motor working current digital signals from the storage content at a preset period aiming at each class of motor working current digital signals after classified storage; preferably, the preset period may be set according to different lengths of time that the motor is put into operation, specifically, if the motor is currently in the device putting period (the length of time that the motor is put into operation is less than the first preset time), the preset period is generally a short period less than a limit value of the first period, if the motor is currently in the operation stable period (the length of time that the motor is put into operation is greater than the second preset time), the preset period is generally a long period greater than a limit value of the second period, if the motor is currently in the aging period (the length of time that the motor is put into operation is greater than the third preset time), the preset period is generally a short period less than a limit value of the third period, and the value of the third period may be equal to the limit value of the first; preferably, before the step 4, a step of formulating an extraction strategy of the plurality of motor working current digital signals according to the condition of the motor working time length can be further included, that is, the predetermined period is adjusted and set according to the condition of the motor working time length;
and 5: taking the classification category of the currently extracted motor working current digital signals as a condition, and obtaining a motor working condition diagnosis result based on the variation trend of the extracted plurality of motor working current digital signals; the motor working condition diagnosis result can comprise motor coil aging, magnetic weakening of a magnetic cylinder, working voltage reduction, power load increase, mechanical interference, mechanical abnormal abrasion and the like.
As a further preferred embodiment, fig. 2 shows an exemplary flowchart of step 5 in embodiment 1 of the present invention, and as shown in fig. 2, further, the step of outputting a motor operating condition diagnosis result based on a variation trend of the extracted plurality of motor operating current digital signals by using a classification category of the currently extracted motor operating current digital signal as a condition specifically includes:
step 51: determining the motor working current digital signals belonging to abnormal data points based on the variation trend of the extracted plurality of motor working current digital signals by taking the classification category of the currently extracted motor working current digital signals as a condition;
step 52: taking a plurality of different abnormal data points as sample data, and adding labels of corresponding motor working condition diagnosis results to the sample data;
step 53: performing machine learning training on the sample data and establishing a machine learning model, wherein the machine learning model is used for outputting a motor working condition diagnosis result under the condition that a plurality of motor working current digital signals in a preset period are input; in practical application, the extracted digital signals of the working currents of the plurality of motors can be subjected to fitting operation, ideally, a horizontal line of micro-oscillation is obtained, and in actual conditions, individual or few points which violently go up or down frequently occur sporadically and then return to the micro-oscillation, the point deviating from the micro-oscillation horizontal line by the preset vertical distance can be used as an abnormal data point, the motor working condition diagnosis result (the abnormal type is manually set or the neglect treatment is selected) aiming at the abnormal data point is input by a user, the machine self-learns and memorizes the corresponding motor working condition diagnosis result, after a certain amount of data storage and point drawing, the horizontal line will gradually become an upward or downward trend, by analogy, if a machine learns a certain number of anomaly types and processing modes, a corresponding machine learning model can be formed.
The method for monitoring the working condition of the motor according to this embodiment may be executed by a processor and a memory built in an automatic teller machine, an ATM machine, or other devices connected to the above devices, such as a processing device, a monitoring terminal, a monitoring system, and the like.
The embodiment and the preferred embodiment can realize the periodic analysis of the change trend of the working current of the motor, and can identify whether the motor operates abnormally or not in advance by combining a machine learning mode, and start early warning in advance before the motor fails and is not enough to trigger an alarm signal, so that a maintainer is guided and timely arranged to overhaul or shut down the motor, further damage to self-service financial equipment caused by motor problems can be prevented, so that an equipment manager can intuitively know the operating state of the motor according to the motor, the motor is timely replaced, and the operating efficiency of the self-service financial equipment is improved.
The invention also provides a preferred embodiment which is further improved on the basis of the embodiment 1, and further, a processing opinion label is added to the sample data while a corresponding motor working condition diagnosis result label is added to the sample data; the machine learning model outputs a corresponding processing suggestion while outputting a motor working condition diagnosis result; the processing opinion can be an exception processing mode or scheme aiming at the exception diagnosis result of the working condition of the motor; furthermore, when the working condition of the motor is abnormal, a user can be reminded to replace or maintain the motor.
The present invention further provides a motor working condition monitoring device, fig. 3 is a structural block diagram of the motor working condition monitoring device according to embodiment 1 of the present invention, and the motor working condition monitoring device shown in fig. 3 includes: an acquisition part 1, an A/D conversion part 2, a storage part 3, an extraction part 4 and a processing part 5; the collecting part 1 is configured to collect a motor working current; the A/D conversion part 2 is configured to perform AD conversion on the collected motor working current to obtain a motor working current digital signal; the storage part 3 is configured to store the motor working current digital signals in a classified manner according to a preset classification rule; the extracting part 4 is configured to extract a plurality of motor operating current digital signals from the stored contents at a predetermined cycle for each class of motor operating current digital signals after being classified and stored; the processing part 5 is configured to obtain a motor working condition diagnosis result based on a variation trend of the extracted plurality of motor working current digital signals by taking a classification category of the currently extracted motor working current digital signals as a condition; further, the processing section 5 is specifically configured to perform the following operations: determining the motor working current digital signals belonging to abnormal data points based on the variation trend of the extracted plurality of motor working current digital signals by taking the classification category of the currently extracted motor working current digital signals as a condition; taking a plurality of different abnormal data points as sample data, and adding labels of corresponding motor working condition diagnosis results to the sample data; performing machine learning training on the sample data and establishing a machine learning model, wherein the machine learning model is used for outputting a motor working condition diagnosis result under the condition that a plurality of motor working current digital signals in a preset period are input; further, the method is characterized in that the preset classification rule is a motor type, a motor index number, a motor function, a motor working state or a motor service mode; further, the preset period is set according to different working time lengths of the motor; further, while adding a corresponding motor working condition diagnosis result tag to the sample data, the processing unit 5 also adds a processing opinion tag to the sample data; the machine learning model outputs a corresponding processing suggestion while outputting a motor working condition diagnosis result; each module for the motor working condition monitoring device can be realized by corresponding hardware or software units, and each module can be an independent software unit or hardware unit, and can also be integrated into one software unit or hardware unit of the terminal; the processing unit 5 may adopt a hardware acceleration computing platform composed of FPGA and ARM.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (6)
1. An electric machine working condition monitoring method is characterized by comprising the following steps:
collecting the working current of a motor, and amplifying the working current of the motor according to a preset multiple;
performing AD conversion on the amplified motor working current to obtain a motor working current digital signal;
classifying and storing the motor working current digital signals according to a preset classification rule;
aiming at each class of motor working current digital signals after classified storage, extracting a plurality of motor working current digital signals from storage contents in a preset period, wherein the preset period is set according to different working time lengths of motors;
taking the classification category of the currently extracted motor working current digital signals as a condition, and performing fitting operation based on the extracted plurality of motor working current digital signals to obtain a horizontal line;
taking a point deviating from the preset vertical distance of the horizontal line as an abnormal data point, and determining a motor working current digital signal belonging to the abnormal data point;
taking a plurality of different abnormal data points as sample data, and adding labels of corresponding motor working condition diagnosis results to the sample data;
and performing machine learning training on the sample data and establishing a machine learning model, wherein the machine learning model is used for outputting a motor working condition diagnosis result under the condition that a plurality of motor working current digital signals in a preset period are input.
2. The method of claim 1, wherein the predetermined classification rule is a motor type, a motor index number, a motor function, a motor operating status, and/or a motor traffic pattern.
3. The method according to claim 1, wherein a processing opinion tag is added to the sample data while a corresponding motor condition diagnosis result tag is added to the sample data; and the machine learning model outputs a corresponding processing suggestion while outputting a motor working condition diagnosis result.
4. An electric machine condition monitoring device, the device comprising:
the acquisition part is configured to acquire a motor working current and amplify the motor working current according to a preset multiple;
an A/D conversion section configured to AD-convert the amplified motor operating current to obtain a motor operating current digital signal;
a storage section configured to store the motor operating current digital signals in a classified manner according to a preset classification rule;
an extraction section configured to extract a plurality of motor operating current digital signals from the stored contents at a predetermined cycle for each of the motor operating current digital signals after the classification storage, the predetermined cycle being set according to a difference in an operating time period during which the motor is put into operation; and
a processing section configured to perform fitting operation based on the extracted plurality of motor operating current digital signals, taking a classification category of the currently extracted motor operating current digital signal as a condition, resulting in a horizontal line;
taking a point deviating from the preset vertical distance of the horizontal line as an abnormal data point, and determining a motor working current digital signal belonging to the abnormal data point;
taking a plurality of different abnormal data points as sample data, and adding labels of corresponding motor working condition diagnosis results to the sample data;
and performing machine learning training on the sample data and establishing a machine learning model, wherein the machine learning model is used for outputting a motor working condition diagnosis result under the condition that a plurality of motor working current digital signals in a preset period are input.
5. The device for monitoring the working condition of the motor according to claim 4, wherein the preset classification rule is a motor type, a motor index number, a motor function, a motor working state and/or a motor service mode.
6. The motor operating condition monitoring device according to claim 4, wherein the processing section further adds a processing opinion tag to the sample data while adding a corresponding motor operating condition diagnosis result tag to the sample data; and the machine learning model outputs a corresponding processing suggestion while outputting a motor working condition diagnosis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711425098.5A CN108152738B (en) | 2017-12-25 | 2017-12-25 | Motor working condition monitoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711425098.5A CN108152738B (en) | 2017-12-25 | 2017-12-25 | Motor working condition monitoring method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108152738A CN108152738A (en) | 2018-06-12 |
| CN108152738B true CN108152738B (en) | 2020-09-15 |
Family
ID=62462585
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711425098.5A Active CN108152738B (en) | 2017-12-25 | 2017-12-25 | Motor working condition monitoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108152738B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109188269A (en) * | 2018-07-17 | 2019-01-11 | 北京新水源景科技股份有限公司 | Judge the method for electrical fault |
| CN109274071A (en) * | 2018-09-14 | 2019-01-25 | 河南森尼瑞电气有限公司 | A kind of motor protector intelligent monitoring and early warning system and method based on Internet of Things |
| CN110608785B (en) * | 2019-08-22 | 2022-07-05 | 安徽省法米特物联技术有限公司 | Internet of things pressure liquid level meter and liquid level measurement method |
| JP7434838B2 (en) * | 2019-11-26 | 2024-02-21 | 富士電機機器制御株式会社 | Diagnostic equipment, distribution boards, control panels, diagnostic methods and machine diagnostic programs |
| US20220397608A1 (en) * | 2020-01-09 | 2022-12-15 | Mitsubishi Electric Corporation | Machine learning apparatus and machine learning method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201440605U (en) * | 2009-04-23 | 2010-04-21 | 秦皇岛融大工程技术有限公司 | Motor self-diagnostic protective device |
| CN103185862A (en) * | 2011-12-31 | 2013-07-03 | 上海汽车集团股份有限公司 | Method and device for diagnosis of direct current motor breakdown in automobile starter |
| CN106842031A (en) * | 2017-04-20 | 2017-06-13 | 哈尔滨理工大学 | Integrated motor intellectuality big data on-Line Monitor Device |
| CN107091986A (en) * | 2017-05-23 | 2017-08-25 | 河海大学 | ANFIS wind-powered electricity generation double fed asynchronous machine air-gap eccentric fault diagnostic classification methods |
| CN107247230A (en) * | 2017-07-03 | 2017-10-13 | 浙江大学 | A kind of electric rotating machine state monitoring method based on SVMs and data-driven |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060165292A1 (en) * | 2005-01-26 | 2006-07-27 | Xerox Corporation. | Noise resistant edge detection |
| CN105652202A (en) * | 2015-12-23 | 2016-06-08 | 中国石油大学(华东) | Submersible motor fault diagnosis method based on temperature field detection |
| CN107192951B (en) * | 2017-07-31 | 2019-07-23 | 湖南科技大学 | A kind of micro- method for diagnosing faults of wind-driven generator three-phase rotor current |
-
2017
- 2017-12-25 CN CN201711425098.5A patent/CN108152738B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201440605U (en) * | 2009-04-23 | 2010-04-21 | 秦皇岛融大工程技术有限公司 | Motor self-diagnostic protective device |
| CN103185862A (en) * | 2011-12-31 | 2013-07-03 | 上海汽车集团股份有限公司 | Method and device for diagnosis of direct current motor breakdown in automobile starter |
| CN106842031A (en) * | 2017-04-20 | 2017-06-13 | 哈尔滨理工大学 | Integrated motor intellectuality big data on-Line Monitor Device |
| CN107091986A (en) * | 2017-05-23 | 2017-08-25 | 河海大学 | ANFIS wind-powered electricity generation double fed asynchronous machine air-gap eccentric fault diagnostic classification methods |
| CN107247230A (en) * | 2017-07-03 | 2017-10-13 | 浙江大学 | A kind of electric rotating machine state monitoring method based on SVMs and data-driven |
Non-Patent Citations (1)
| Title |
|---|
| 基于设备故障相关参数筛选模型建立风电机组故障预警体系;陈晓清 等;《风能》;20141231(第10期);第92-96页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108152738A (en) | 2018-06-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108152738B (en) | Motor working condition monitoring method and device | |
| CN109947080B (en) | Fault diagnosis method and device, computer storage medium and terminal | |
| US11269322B2 (en) | Failure diagnosis system | |
| CA2567661A1 (en) | Cash dispensing automated banking machine diagnostic system and method | |
| EP3319050A1 (en) | Vehicle operation data collection apparatus, vehicle operation data collection system, and vehicle operation data collection method | |
| CN116529615A (en) | Method for predicting life of lithium ion battery, method for predicting discharge capacity maintenance rate, program for predicting life, program for predicting discharge capacity maintenance rate, and information processing apparatus | |
| CN113687234B (en) | Battery abnormality recognition method, apparatus, device, medium, and program product | |
| JP7483922B2 (en) | Battery diagnostic device, battery diagnostic method, battery pack and automobile | |
| EP2149980A2 (en) | Stray flux processing method and system | |
| CN106384611B (en) | Nuclear power station rod control system test device and method | |
| JP2002091548A (en) | Bcu control system | |
| CN115327417A (en) | Early warning method and system for abnormity of power battery monomer and electronic equipment | |
| CN111025153A (en) | Electric vehicle battery fault diagnosis method and device | |
| CN117192347A (en) | High-voltage circuit breaker on-line monitoring and fault diagnosis system and method | |
| EP2840402B1 (en) | Operating state estimating device for electrical apparatus, operating state estimating method for electrical apparatus, program, feature vector registration device for electrical apparatus, feature vector registration method for electrical apparatus, server apparatus, and operating state estimating system for electrical apparatus | |
| CN102213685A (en) | Nuclear magnetic resonance (NMR) device for oiliness seed automatic test and intelligent sorting | |
| CN101910851B (en) | Load current monitoring device and load power monitoring device | |
| CN111896883A (en) | Vehicle-mounted storage battery supportable parking time prediction method and early warning method | |
| CN116955071A (en) | Fault classification method, device, equipment and storage medium | |
| CN116953413A (en) | Fault diagnosis system based on components and parts in cubical switchboard | |
| KR20220012236A (en) | Estimation method of internal resistance of secondary battery and abnormality detection system of secondary battery | |
| Nandi et al. | Diagnosis of induction motor faults using frequency occurrence image plots—a deep learning approach | |
| CN115480944A (en) | Black screen fault analysis method and device of vehicle-mounted entertainment terminal, vehicle and medium | |
| CN111597957B (en) | Transformer winding fault diagnosis method based on morphological image processing | |
| CN106707155A (en) | Small-capacity contactor acting characteristic test system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |