CN115078992A - Motor health condition early warning monitoring method based on artificial intelligence - Google Patents
Motor health condition early warning monitoring method based on artificial intelligence Download PDFInfo
- Publication number
- CN115078992A CN115078992A CN202210648230.3A CN202210648230A CN115078992A CN 115078992 A CN115078992 A CN 115078992A CN 202210648230 A CN202210648230 A CN 202210648230A CN 115078992 A CN115078992 A CN 115078992A
- Authority
- CN
- China
- Prior art keywords
- motor
- motors
- heat dissipation
- health condition
- data set
- 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
- 230000036541 health Effects 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012544 monitoring process Methods 0.000 title claims abstract description 27
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 23
- 230000017525 heat dissipation Effects 0.000 claims abstract description 84
- 230000000694 effects Effects 0.000 claims abstract description 35
- 238000005259 measurement Methods 0.000 claims abstract description 22
- 238000013459 approach Methods 0.000 claims abstract description 13
- 230000008859 change Effects 0.000 claims description 57
- 238000005070 sampling Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 4
- 230000000875 corresponding effect Effects 0.000 description 42
- 238000012545 processing Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000002360 explosive Substances 0.000 description 2
- 230000003862 health status Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 238000007373 indentation Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tests Of Circuit Breakers, Generators, And Electric Motors (AREA)
Abstract
The invention discloses a motor health condition early warning and monitoring method based on artificial intelligence, which comprises the following steps: a001: obtaining the working voltage balance effect of the motor and the vibration capability of the motor; a002: acquiring the approach level between two random motors, and acquiring the difference between the two motors according to the approach level; a003: obtaining a first operating health condition of each motor in the same category; a004: obtaining the heat dissipation capacity of the motor; a005: obtaining a second operating health condition of each motor in the same category; a006: and carrying out early warning monitoring prompt on the health condition of the motor according to the measurement reference value. The early warning monitoring to the motor working condition combines the artificial intelligence technology in this technical scheme, makes the monitoring early warning accuracy to motor work higher, and is also more reliable, has avoided adopting the manpower to maintain the motor and probably appears omitting or postponing the circumstances of maintaining to the normal orderly operation of motor work has been ensured.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a motor health condition early warning and monitoring method based on artificial intelligence.
Background
With the development of electrical automation, more and more industries need motors to help expand their production. Therefore, the motor is operated in overtime and overtime in more industries, and is often in an overload working state, which easily causes the abnormal operation of the motor. Especially, some motors which are easy to burn and explode have strict explosion-proof requirements when in use, if the motor does not work normally in the working process, the bearing is abnormal, such as the vibration frequency changes, the power supply voltage changes, and the like, so that the temperature rises, and the possibility of flammability and explosion increases.
The conventional motor health condition detection method mainly depends on manual regular maintenance and repair, but under the condition that a large number of motors need to be maintained, omission occurs inevitably, the labor cost is too high, and the detection accuracy of the motor operation health condition is reduced.
With the rapid development of the artificial intelligence technology, the data processing and information analysis technology in the field of artificial intelligence is considered to be applied to the early warning and monitoring of the working condition of the motor.
Disclosure of Invention
The invention provides a motor health condition early warning monitoring method based on artificial intelligence, which is characterized in that a first operation health condition and a second operation health condition corresponding to each motor are obtained, a measurement reference value is combined to be compared with a set minimum threshold value for measuring the working condition of the motor, and if the measurement reference value is higher than the set minimum threshold value, early warning prompt is carried out, so that the early warning accuracy of the motor health working condition is improved. The problem of the adoption manpower that prior art exists maintain with the maintenance motor probably the omission condition appears to and the lower technical problem of manpower maintenance accuracy is solved.
The invention is realized by the following technical scheme:
the motor health condition early warning and monitoring method based on artificial intelligence comprises the following steps:
a001: acquiring a power supply voltage change data set and a vibration frequency change data set of the motor within a period of time, acquiring a working voltage balance effect of the motor according to the power supply voltage change data set, and acquiring the vibration capability of the motor according to the vibration frequency change data set;
a002: acquiring an approaching level between two random motors, wherein the approaching level is obtained through the corresponding working voltage balance effect and vibration capacity of the two motors, and the distinguishing degree between the two motors is obtained according to the approaching level;
a003: classifying all the motors according to the difference between the two motors, and obtaining a first operation health condition of each motor in the same classification according to the working voltage balance effect in the same classification;
a004: acquiring an external temperature change data set and an internal temperature change data set of the motor within a period of time, and acquiring the heat dissipation capacity of the motor according to the maximum value of the difference between the external temperature change data set and the internal temperature change set;
a005: obtaining a heat dissipation difference between the two motors according to the heat dissipation capacity and the vibration capacity corresponding to the two motors at random, obtaining a heat dissipation capacity difference between the two motors according to the heat dissipation difference, reclassifying all the motors according to the heat dissipation capacity difference, and obtaining a second operation health condition of each motor in the same classification according to the reclassified same classification heat dissipation capacity;
a006: multiplying the first operation health condition and the second operation health condition of each motor to be used as a measurement reference value of the motor, and carrying out early warning monitoring prompt on the health condition of the motor according to the measurement reference value.
Optionally, in step a002, the approaching levels of the two motors are obtained according to the working voltage balancing effect and the vibration capability corresponding to the two motors:
wherein W (X, Y) represents the approximate level between the Xth motor and the Yth motor, avgQ X Average, avgQ, of the data set representing the variation of supply voltage of the Xth motor Y Mean value, Qx, of a data set representing the variation of the supply voltage of the Y-th motor n Representing the working voltage balancing effect, Q, of the Xth motor sampled at the nth time Yn Expressing the working voltage balance effect of the Nth sampling Yth motor, K X Denotes the vibration capability of the Xth motor, K Y Indicating the vibration capability of the Yth motor, gamma 1 Reference factor, gamma, for the balancing effect of the operating voltage 2 Is a reference factor for the ability to vibrate.
Alternatively, in step a002, the method for obtaining the degree of distinction between the two motors according to the proximity level is: randomly selecting one motor as a designated motor, acquiring the approximate horizontal sum between the designated motor and other motors, acquiring the attachment degree of the designated motor through the approximate horizontal sum, and subtracting the attachment degrees corresponding to the two random motors to obtain the discrimination degree.
Optionally, the degree of attachment for a given motor obtained by approximating the sum of the levels is:
M X ＝1/(1+∑(1-W(X,Z)))
wherein M is X Which indicates the degree of attachment of the xth motor, i.e., the degree of attachment of the designated motor, W (X, Z) is the level of approach between the xth motor and the xth motor.
Optionally, in step a003, all the motors are classified according to the degree of distinction between the two motors, and each classified motor is arranged according to the characteristic power supply voltage balance factors of all the motors in the same classification, where the characteristic power supply voltage balance factor of each motor is obtained by:
wherein R is Z Characteristic supply voltage balance factor, Q, for the Z-th motor in the same class n And e is a natural constant, and represents the power supply voltage balance effect of the motor when the data is acquired for the nth time.
Optionally, in step a003, the first operating health condition of each motor in the same category is obtained as:
D S ＝G s /T
wherein D is S Is the first operating health condition of the S category, G S For the ranking of the S-th category in the arrangement, T represents the number of all categories.
Alternatively, in step a 004: the method for acquiring the external temperature change data set and the internal temperature change data set of the motor in a period of time comprises the following steps: temperature sensors are placed in the motor and outside the motor shell, temperature changes of the motor and the motor shell are collected, and the frequency of temperature data collection is set, so that an external temperature change data set and an internal temperature change data set of the motor in a period of time are obtained.
Optionally, in step a004, obtaining the heat dissipation capability of the motor according to the external temperature change data set and the maximum value of the difference between the internal temperature change sets is:
H＝tanh(max(U nn -U wn ))*α
wherein H represents the heat dissipation capability of the motor, U nn Internal temperature data, U, corresponding to the motor at the time of the nth data acquisition wn The external temperature data corresponding to the motor when the data are acquired for the nth time is shown, max is a maximum function, alpha is an adjusting factor, and tanh is a hyperbolic tangent function.
Optionally, in step a005, the heat dissipation difference between the two motors is obtained according to the heat dissipation capacity and the vibration capacity corresponding to the two motors:
wherein, F (X, Y) is the heat dissipation difference between the X motor and the Y motor; ex denotes the heat dissipation level of the Xth motor, E Y Indicating the heat dissipation level of the Yth motor, Kx indicating the vibration capability of the Xth motor, K Y Denotes the vibration capability of the Y-th motor, j denotes an importance factor of the vibration capability, and e denotes a natural constant.
Optionally, in step a005, after obtaining the heat dissipation difference between any one motor and another motor, obtaining the heat dissipation capability corresponding to the motor is:
L＝(1/c)*∑F(X，Z)
wherein, L represents the corresponding heat dissipation capacity of the motor, F (X, Z) represents the heat dissipation difference between the Xth motor and the Zth motor, and C represents the number of all the motors.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1) according to the technical scheme, the power supply voltage change data set and the vibration frequency change data set of the motor within a period of time are acquired, the working voltage balance effect of the motor is acquired according to the power supply voltage change data set, the vibration capability of the motor is acquired according to the vibration frequency change data set, and the acquired working voltage balance effect and vibration capability are stored in the database so as to increase persuasion of a data processing result.
2) The motors are reclassified based on the heat dissipation levels and the vibration capabilities among the different motors, ranked according to differences in heat dissipation levels among the motors in each classification, and a second operational health of the motors in each classification is obtained. According to the first operation health condition and the second operation health condition corresponding to each motor, the first operation health condition and the second operation health condition are combined to multiply to obtain a measurement reference value of the motor, the measurement reference value is compared with a set lowest threshold value for measuring the working condition of the motor, and if the measurement reference value is higher than the set lowest threshold value, early warning prompt is carried out, so that the early warning accuracy of the working condition of the motor is improved. The artificial intelligence technology is applied to real-time monitoring of motor work, so that the motor work is ensured, potential risks such as flammability and explosiveness are early warned in advance, preventive measures are convenient to take in advance, and meanwhile, compared with manual maintenance, the artificial intelligence motor early warning device is high in maintenance efficiency and high in work accuracy.
Drawings
FIG. 1 is a block diagram illustrating a flow structure of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not used as limitations of the present invention.
Example 1:
as shown in fig. 1, the motor health condition early warning and monitoring method based on artificial intelligence comprises the following steps:
a001: acquiring a power supply voltage change data set and a vibration frequency change data set of the motor within a period of time, acquiring a working voltage balance effect of the motor according to the power supply voltage change data set, and acquiring the vibration capability of the motor according to the vibration frequency change data set;
specifically, the stator magnetic flux of the motor approaches a saturation state due to the excessively high supply voltage of the motor, the current sharply increases, the motor efficiency increases, and the heat is seriously generated, thereby causing the motor to work abnormally, and therefore, the supply voltage needs to be ensured within a certain range. Monitoring the change condition of the power supply voltage in the working process of the motor to obtain a power supply voltage change data set;
meanwhile, in the operation process of the motor, iron loss, copper loss, mechanical loss and additional loss can be generated in the long-term operation process of the motor, the motor is particularly and obviously embodied, the motor vibration frequency can be directly influenced by the abrasion of the motor, the vibration frequency is abnormal, and the vibration sound is large.
The vibration frequency of the motor is quite sensitive to damage to the motor bearings, such as flaking, indentation, corrosion, cracking, wear, etc., which are reflected in the vibration frequency. When the motor is abnormal, the vibration frequency of the motor can show a larger difference value.
The vibration frequency of the motor is monitored in real time, a vibration frequency change data set of the motor is obtained, and the vibration capacity of the motor is obtained through the vibration frequency change data set.
The vibration frequency of the motor can be acquired for 2 times per second, and the acquisition time lasts for 5 minutes, so that a vibration frequency change data set corresponding to the motor within 5 minutes is obtained. In this embodiment, the vibration frequency of the motor may be detected by using an inertial vibration sensor. The power supply voltage can be detected in real time by a voltage detection device, so that data can be obtained. If the supply voltage of the motor is measured once per second for 5 minutes, a supply voltage data set for the motor for 5 minutes is obtained.
In order to improve the reliability of data analysis of a motor power supply voltage change data set, a vibration frequency data set and the like, the corresponding working voltage balance effect and the vibration capability are stored in a database, so that the subsequent further analysis is facilitated.
This embodiment detects like the motor through the health condition to the motor, the mains voltage of motor etc. in case the motor has the unusual then in time sends out the early warning, promotes the early warning ability of motor.
A002: acquiring an approaching level between two random motors, wherein the approaching level is obtained through the corresponding working voltage balance effect and vibration capacity of the two motors, and the distinguishing degree between the two motors is obtained according to the approaching level;
a003: classifying all the motors according to the difference between the two motors, and obtaining a first operation health condition of each motor in the same classification according to the working voltage balance effect in the same classification;
in particular, the bearings of the motor are usually paired, that is, there are two bearings in one motor, but in actual use, the number of the motors used in the device is more than one, and thus the operation health conditions of the motors are affected differently. Therefore, classification is carried out according to the difference degree of the motors, and the processing operation amount of acquired data is greatly reduced. Wherein, the level of approach between two random motors is:
wherein W (X, Y) represents the approximate level between the Xth motor and the Yth motor, avgQ X Average, avgQ, of the data set representing the variation of supply voltage of the Xth motor Y Mean value, Qx, of a data set representing the variation of the supply voltage of the Y-th motor n Representing the working voltage balancing effect, Q, of the Xth motor sampled at the nth time Yn Expressing the working voltage balance effect of the Nth sampling Yth motor, K X Denotes the vibration capability of the Xth motor, K Y Indicating the vibration capability of the Yth motor, gamma 1 Reference factor, gamma, for the balancing effect of the operating voltage 2 Is a reference factor for the ability to vibrate.
Wherein, regarding gamma 1 、γ 2 Can be set according to actual conditions, and in the embodiment, can be set as gamma 1 ＝0.8、γ 2 ＝0.2。
Based on the method for calculating the same approach level, the approach level of the vibration capability and the power supply voltage balance effect between any two motors in all the motors is obtained, the operation health condition of each motor is analyzed, and classification or grouping is carried out according to the analysis.
The method for obtaining the degree of distinction between the two motors according to the approach level is as follows: randomly selecting one motor as a designated motor, acquiring the approximate horizontal sum between the designated motor and other motors, acquiring the attachment degree of the designated motor through the approximate horizontal sum, and subtracting the attachment degrees corresponding to the two random motors to obtain the discrimination degree.
Optionally, the degree of attachment for a given motor obtained by approximating the sum of the levels is:
M X ＝1/(1+∑(1-W(X,Z)))
wherein M is X Indicates the degree of attachment of the xth motor, i.e., the degree of attachment of the designated motor, and W (X, Z) is the level of approach between the xth motor and the xth motor.
According to the method for obtaining the degree of attachment of the designated motor, the corresponding degree of attachment of each motor is obtained, and the degree of distinction between every two motors is obtained according to the difference between the degrees of attachment of the motors.
Classifying or grouping according to the obtained distinguishing degree between the motors and the size range of the distinguishing degree, specifically adopting a DBSCAN density clustering algorithm to set the size of the distinguishing degree range, and realizing the classification of all the motors.
Specifically, all motors are classified according to the degree of distinction between the two motors, each classified motor is arranged according to the characteristic power supply voltage balance factors of all the motors in the same classification, and the characteristic power supply voltage balance factor of each motor is obtained by the following method:
wherein R is Z Characteristic supply voltage balance factor, Q, for the Z-th motor in the same class n And e is a natural constant, and represents the power supply voltage balance effect of the motor when the data is acquired for the nth time.
Based on the method for obtaining the characteristic power supply voltage balance factors of the motors, the characteristic power supply voltage balance factors corresponding to all the motors in the same classification are obtained, the average value of the characteristic power supply voltage balance factors corresponding to all the motors in each classification or each group is calculated, then all the classifications or the groups are arranged according to the corresponding average value in each classification, and when the average value of the corresponding characteristic power supply voltage balance factors in each classification is smaller, the arrangement corresponding to the classification is arranged more forward.
The first operation health status is positively correlated with the operation voltage balance effect in the classification. Obtaining a first operating health condition for each motor in the same category as:
D S ＝G s /T
wherein D is S Is the first operating health condition of the S category, G S For the S-th category' S rank in the arrangement, T represents the number of all categories.
And according to the obtained first operation health condition in each classification or grouping, distributing the corresponding first operation health condition in the classification to each motor in the classification, namely that each motor in the same classification corresponds to the same first operation health condition, namely that the better the working voltage balance effect of each motor in the same classification is, the better the first operation health condition of each corresponding motor is.
A004: acquiring an external temperature change data set and an internal temperature change data set of the motor within a period of time, and acquiring the heat dissipation capacity of the motor according to the maximum value of the difference between the external temperature change data set and the internal temperature change set;
when the motor actually works, the mechanical loss of the motor can be converted into heat energy, and on the other hand, the heat energy is absorbed by the motor, so that the motor generates heat and the temperature is increased. The heat that produces of motor itself can make the temperature rise promptly, if the heat that produces can not in time distribute, not only can influence the normal work of motor, if reach when inflammable and explosive's injecing moreover, can produce bigger danger.
In the technical scheme, the temperature sensor is arranged in the motor and used for collecting the internal temperature of the motor in the actual working process, and meanwhile, the temperature sensor is arranged outside the shell of the motor and used for collecting the external temperature of the motor.
The frequency of acquiring the temperature data of the motor can be 2 times per second, and an external temperature change data set and an internal temperature change data set of the motor within 1 minute are acquired.
Specifically, the heat dissipation capability of the motor obtained according to the external temperature change data set and the maximum value of the difference value of the internal temperature change set is as follows:
H＝tanh(max(U nn -U wn ))*α
wherein H represents the heat dissipation capacity of the motor, U nn Internal temperature data, U, corresponding to the motor at the time of the nth data acquisition wn The motor temperature control method is characterized by comprising the following steps of representing external temperature data corresponding to the motor when data are collected for the nth time, representing a maximum function by max, representing an adjustment factor by alpha, and representing a constant by tanh, wherein the tanh is a hyperbolic tangent function.
The adjustment factor α in the present embodiment is 3/[ max (U) nn -U wn )]The setting can be made empirically, and specifically, α can be set to 0.6, that is, the default maximum heat dissipation amount is 6 ℃.
The heat dissipation capacity data corresponding to different motors are stored in the database, the database is continuously updated, sufficient data volume is ensured, and the actually acquired data of the health condition of the motors and the data in the database are compared and analyzed, so that the reliability of the data when the motors are compared is improved.
A005: obtaining a heat dissipation difference between the two motors according to the heat dissipation capacity and the vibration capacity corresponding to the two motors at random, obtaining a heat dissipation capacity difference between the two motors according to the heat dissipation difference, reclassifying all the motors according to the heat dissipation capacity difference, and obtaining a second operation health condition of each motor in the same classification according to the reclassified same classification heat dissipation capacity;
specifically, since the heat dissipation capability of the motor is not only related to the structure of the motor itself, but also related to the external environment, the heat dissipation difference between the two motors obtained according to the heat dissipation capability and the vibration capability corresponding to the two motors is:
wherein, F (X, Y) is the heat dissipation difference between the X motor and the Y motor; ex denotes the heat dissipation level of the Xth motor, E Y Indicating the heat dissipation level of the Yth motor, Kx indicating the vibration capability of the Xth motor, K Y Denotes the vibration capability of the Y-th motor, j denotes an importance factor of the vibration capability, and e denotes a natural constant.
In the calculation of the heat dissipation difference between the two motors, although the vibration frequency of the motor has a certain influence on the heat dissipation capability, the vibration frequency of the motor cannot be completely determined to be abnormal with the vibration frequency of the motor, so that the heat dissipation capability of the motor is greatly influenced.
Therefore, the vibration performance is subjected to the importance factor processing, and j is 0.3 in the present embodiment. And acquiring the heat dissipation difference sum between any motor and other motors, and acquiring the heat dissipation capacity of the motors according to the heat dissipation difference sum, wherein the difference value between the heat dissipation capacities corresponding to any two motors is the heat dissipation capacity difference.
After obtaining the heat dissipation difference between any motor and other motors, the heat dissipation capacity that obtains this motor correspondence is:
L＝(1/c)*∑F(X，Z)
wherein, L represents the heat dissipation ability that this motor corresponds, and F (X, Z) represents the heat dissipation difference between the Xth motor and the Z th motor, and C represents all motor quantity.
And obtaining the heat dissipation capacity corresponding to each motor, taking the difference between the heat dissipation capacities of the two motors as the difference between the heat dissipation capacities of the two motors, and classifying all the motors again according to the difference between the heat dissipation capacities. The classification method adopts a DBSCN density clustering algorithm to realize the purpose of classifying or grouping the motors.
And arranging each group or each class which is classified again according to the heat dissipation capacity of the motors in each group so as to obtain the sum of the heat dissipation capacity of the motors in each group, calculating the average value of the heat dissipation capacity of the motors in each group according to the sum of the heat dissipation capacity in each group, wherein the smaller the average heat dissipation capacity is, the closer the group or the classified arrangement is to the front.
According to the ranking of each class, calculating a second operation health condition corresponding to the class as follows:
D' S ＝G' s /T'
wherein, D' S Is a first operational health status of S category, G' S For the ranking of the S-th class in the arrangement, T' represents the number of all classes clustered.
Therefore, the second operation health conditions corresponding to each category or each group are subjected to clustering analysis, the second operation health conditions corresponding to the categories are arranged to each motor in each category, namely each motor in the same category has the same second operation health condition, the heat dissipation capacity of each motor in the category is better, and the second operation health condition value corresponding to each corresponding motor is larger.
A006: and multiplying the first operation health condition and the second operation health condition of each motor to be used as a measurement reference value of the motor, and performing early warning monitoring prompt on the operation health condition of the motor according to the measurement reference value.
According to the obtained first operating health condition and the obtained second operating health condition of each motor, each motor has two measurement reference values of the first operating health condition and the second operating health condition, so that the motor can be comprehensively evaluated according to the first operating health condition and the second operating health condition, and the measurement reference value of each motor is as follows:
P A ＝D A *M A *D’ A *L A
wherein, P A For the measured reference value corresponding to the A-th motor, D A Is a first operational health condition, D ', corresponding to the A-th motor' A A second operational health condition corresponding to the A-th motor, L A Is the heat dissipation level of the A-th motor.
And measuring the comprehensive working condition of the motor according to the measurement reference value of each motor, and when the measurement reference value is greater than the set threshold value of the operation health condition, sending out an early warning prompt to prompt that the risk of flammability and explosiveness possibly exists. For different motors, the power supply voltage balance effect of the motors can be distinguished from the requirement of the heat dissipation level, during actual operation, the actual measurement monitoring and measuring results of the different motors can be analyzed, the performance of the motors is further compared by combining data in a database, the measurement reference value is determined to be more accurate, and the measurement reference value is further compared with the set threshold value of the motors, so that the accuracy of early warning and prompting on the healthy working condition of the motors is improved, and the flammable and explosive risks of the motors are reduced.
In this embodiment, a power supply voltage change data set and a vibration frequency change data set of the motor within a period of time are acquired, a working voltage balance effect of the motor is acquired according to the power supply voltage change data set, a vibration capability of the motor is acquired according to the vibration frequency change data set, and the acquired working voltage balance effect and vibration capability are stored in the database to increase persuasion of a data processing result. Calculating according to the approach level between the working voltage balance effect and the vibration capability of the motors, obtaining the attachment degree of the motors according to the approach level between the random motor and other motors, classifying all the motors according to the difference between the attachment degrees corresponding to each motor, arranging each class according to the difference degree of the working voltage balance effect between the motors in the same class, and obtaining the first operation health condition corresponding to each motor in the class. The method comprises the steps of obtaining an internal temperature change data set and an external temperature change data set of a motor during working, obtaining the heat dissipation level of the motor according to the temperature change conditions at the same corresponding moment, and inputting the current related data of the heat dissipation level into a database for storage in order to increase the reliability of data processing.
The motors are reclassified based on the heat dissipation levels and the vibration capabilities among the different motors, ranked according to differences in heat dissipation levels among the motors in each classification, and a second operational health of the motors in each classification is obtained. According to the first operation health condition and the second operation health condition corresponding to each motor, the first operation health condition and the second operation health condition are combined to multiply to obtain a measurement reference value of the motor, the measurement reference value is compared with a set lowest threshold value for measuring the working condition of the motor, and if the measurement reference value is higher than the set lowest threshold value, early warning prompt is carried out, so that the early warning accuracy of the working condition of the motor is improved.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. Motor health condition early warning monitoring method based on artificial intelligence is characterized by comprising the following steps: the method comprises the following steps:
a001: acquiring a power supply voltage change data set and a vibration frequency change data set of the motor within a period of time, acquiring a working voltage balance effect of the motor according to the power supply voltage change data set, and acquiring the vibration capability of the motor according to the vibration frequency change data set;
a002: acquiring an approaching level between two random motors, wherein the approaching level is obtained through the corresponding working voltage balance effect and vibration capacity of the two motors, and the distinguishing degree between the two motors is obtained according to the approaching level;
a003: classifying all the motors according to the difference between the two motors, and obtaining a first operation health condition of each motor in the same classification according to the working voltage balance effect in the same classification;
a004: acquiring an external temperature change data set and an internal temperature change data set of the motor within a period of time, and acquiring the heat dissipation capacity of the motor according to the maximum value of the difference between the external temperature change data set and the internal temperature change set;
a005: obtaining a heat dissipation difference between the two motors according to the heat dissipation capacity and the vibration capacity corresponding to the two motors at random, obtaining a heat dissipation capacity difference between the two motors according to the heat dissipation difference, reclassifying all the motors according to the heat dissipation capacity difference, and obtaining a second operation health condition of each motor in the same classification according to the reclassified same classification heat dissipation capacity;
a006: multiplying the first operation health condition and the second operation health condition of each motor to be used as a measurement reference value of the motor, and carrying out early warning monitoring prompt on the health condition of the motor according to the measurement reference value.
2. The artificial intelligence based motor health condition early warning and monitoring method according to claim 1, wherein: in step a002, the approximate levels of the two motors are obtained according to the working voltage balance effect and the vibration capability corresponding to the two random motors:
wherein W (X, Y) represents the approximate level between the Xth motor and the Yth motor, avgQ X Average value, avgQ, of data set representing variation of supply voltage of Xth motor Y Mean value, Qx, of a data set representing the variation of the supply voltage of the Y-th motor n Representing the working voltage balancing effect, Q, of the Xth motor sampled at the nth time Yn Expressing the working voltage balance effect of the Nth sampling Yth motor, K X Denotes the vibration capability of the Xth motor, K Y Indicating the vibration capability of the Yth motor, gamma 1 Reference factor, gamma, for the balancing effect of the operating voltage 2 Is a reference factor for the ability to vibrate.
3. The artificial intelligence based motor health warning and monitoring method according to claim 2, wherein: in step a002, the method for obtaining the degree of distinction between the two motors according to the approach level is: randomly selecting one motor as a designated motor, acquiring the approximate horizontal sum between the designated motor and other motors, acquiring the attachment degree of the designated motor through the approximate horizontal sum, and subtracting the attachment degrees corresponding to the two random motors to obtain the discrimination degree.
4. The artificial intelligence based motor health warning and monitoring method according to claim 3, wherein: the degree of attachment for a given motor is obtained by approximating the sum of the levels:
M X ＝1/(1+∑(1-W(X,Z)))
wherein M is X Which indicates the degree of attachment of the xth motor, i.e., the degree of attachment of the designated motor, W (X, Z) is the level of approach between the xth motor and the xth motor.
5. The artificial intelligence based motor health warning and monitoring method according to claim 4, wherein: in step a003, all the motors are classified according to the degree of distinction between the two motors, and each classified motor is arranged according to the characteristic power supply voltage balance factors of all the motors in the same classification, and the method for obtaining the characteristic power supply voltage balance factor of each motor is as follows:
wherein R is Z Characteristic supply voltage balance factor, Q, for the Z-th motor in the same class n And e is a natural constant, and represents the power supply voltage balance effect of the motor when the data is acquired for the nth time.
6. The artificial intelligence based motor health warning and monitoring method according to claim 5, wherein: in step a003, the first operating health condition of each motor in the same category is obtained as follows:
D S ＝G s /T
wherein D is S Is the first operating health condition of the S category, G S For the ranking of the S-th category in the arrangement, T represents the number of all categories.
7. The artificial intelligence based motor health warning and monitoring method according to claim 1, wherein: in step a 004: the method for acquiring the external temperature change data set and the internal temperature change data set of the motor in a period of time comprises the following steps: temperature sensors are placed in the motor and outside the motor shell, temperature changes of the motor and the motor shell are collected, and the frequency of temperature data collection is set, so that an external temperature change data set and an internal temperature change data set of the motor in a period of time are obtained.
8. The artificial intelligence based motor health warning and monitoring method according to claim 1, wherein: in step a004, the heat dissipation capability of the motor obtained according to the external temperature change data set and the maximum value of the difference value of the internal temperature change set is:
H＝[tanh(max(U nn -U wn ))]*α
wherein H represents the heat dissipation capability of the motor, U nn Internal temperature data, U, corresponding to the motor at the time of the nth data acquisition wn The external temperature data corresponding to the motor when the data are acquired for the nth time is shown, max is a maximum function, alpha is an adjusting factor, and tanh is a hyperbolic tangent function.
9. The artificial intelligence based motor health warning and monitoring method according to claim 1, wherein: in step a005, the heat dissipation difference between the two motors is obtained according to the heat dissipation capacity and the vibration capacity corresponding to the two motors:
wherein, F (X, Y) is the heat dissipation difference between the X motor and the Y motor; ex denotes the heat dissipation level of the Xth motor, E Y Indicating the heat dissipation level of the Yth motor, Kx indicating the vibration capability of the Xth motor, K Y Denotes the vibration capability of the Y-th motor, j denotes an importance factor of the vibration capability, and e denotes a natural constant.
10. The artificial intelligence based motor health warning and monitoring method according to claim 9, wherein: in step a005, after the heat dissipation difference between any motor and other motors is obtained, the heat dissipation capability corresponding to the motor is obtained as follows:
L＝(1/c)*∑F(X，Z)
wherein, L represents the corresponding heat dissipation capacity of the motor, F (X, Z) represents the heat dissipation difference between the Xth motor and the Zth motor, and C represents the number of all the motors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210648230.3A CN115078992A (en) | 2022-06-08 | 2022-06-08 | Motor health condition early warning monitoring method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210648230.3A CN115078992A (en) | 2022-06-08 | 2022-06-08 | Motor health condition early warning monitoring method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115078992A true CN115078992A (en) | 2022-09-20 |
Family
ID=83250532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210648230.3A Pending CN115078992A (en) | 2022-06-08 | 2022-06-08 | Motor health condition early warning monitoring method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115078992A (en) |
-
2022
- 2022-06-08 CN CN202210648230.3A patent/CN115078992A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Samanta et al. | Artificial neural networks and genetic algorithm for bearing fault detection | |
| CN106779200A (en) | Based on the Wind turbines trend prediction method for carrying out similarity in the historical data | |
| KR101948604B1 (en) | Method and device for equipment health monitoring based on sensor clustering | |
| CN109100655B (en) | Data processing method and device for power battery | |
| JP7310137B2 (en) | DATA PROCESSING APPARATUS, DATA PROCESSING METHOD, AND COMPUTER PROGRAM | |
| EP3373089A1 (en) | Operating state classification device | |
| CN108956111B (en) | Abnormal state detection method and detection system for mechanical part | |
| Yao et al. | Real-time chatter detection and automatic suppression for intelligent spindles based on wavelet packet energy entropy and local outlier factor algorithm | |
| US11630028B2 (en) | Method and controller for deciding whether a bearing is faulty or not | |
| CN105675038A (en) | Device for predicting faults of instruments | |
| CN110068435A (en) | Vibration analysis system and method | |
| CN110398384A (en) | The machine health monitoring of rotating machinery | |
| CN117074965B (en) | Lithium ion battery remaining life prediction method and system | |
| CN117134007B (en) | Temperature control method and system for lithium ion battery | |
| CN116678552B (en) | Abnormality monitoring method for optical fiber stress sensor in variable temperature environment | |
| CN116345700B (en) | Energy consumption monitoring method and monitoring system for energy storage power station | |
| CN116400126A (en) | Low-voltage power box with data processing system | |
| CN110488188B (en) | Unit three-dimensional health quantitative evaluation method based on dynamic threshold | |
| CN117572837B (en) | Intelligent power plant AI active operation and maintenance method and system | |
| CN117010601B (en) | Data processing method, device, computer equipment and computer readable storage medium | |
| CN115078992A (en) | Motor health condition early warning monitoring method based on artificial intelligence | |
| CN116538092A (en) | Compressor on-line monitoring and diagnosing method, device, equipment and storage medium | |
| CN116433446A (en) | Production safety monitoring method and system based on sensor data interaction | |
| TWI823107B (en) | Learning device, defective detection device and defective detection method | |
| US20180276322A1 (en) | Failure diagnosis apparatus, monitoring apparatus, failure diagnosis method and recording medium |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20220920 |