CN110554316B - Motor fault diagnosis method - Google Patents

Motor fault diagnosis method Download PDF

Info

Publication number
CN110554316B
CN110554316B CN201910870199.6A CN201910870199A CN110554316B CN 110554316 B CN110554316 B CN 110554316B CN 201910870199 A CN201910870199 A CN 201910870199A CN 110554316 B CN110554316 B CN 110554316B
Authority
CN
China
Prior art keywords
fault
motor
membership
mode
array
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
Application number
CN201910870199.6A
Other languages
Chinese (zh)
Other versions
CN110554316A (en
Inventor
王建辉
姚丙雷
刘朋鹏
韦福东
向懿
王辉
徐茜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Electrical Apparatus Research Institute Group Co Ltd
Shanghai Motor System Energy Saving Engineering Technology Research Center Co Ltd
Original Assignee
Shanghai Electrical Apparatus Research Institute Group Co Ltd
Shanghai Motor System Energy Saving Engineering Technology Research Center Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Electrical Apparatus Research Institute Group Co Ltd, Shanghai Motor System Energy Saving Engineering Technology Research Center Co Ltd filed Critical Shanghai Electrical Apparatus Research Institute Group Co Ltd
Priority to CN201910870199.6A priority Critical patent/CN110554316B/en
Publication of CN110554316A publication Critical patent/CN110554316A/en
Application granted granted Critical
Publication of CN110554316B publication Critical patent/CN110554316B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Tests Of Circuit Breakers, Generators, And Electric Motors (AREA)
  • Control Of Electric Motors In General (AREA)

Abstract

The invention relates to a motor fault diagnosis method. According to the motor fault mechanism, the relation between the motor online monitoring data and the fault modes is established, the fault characteristics are obtained from the motor online monitoring data by adopting a fuzzy mathematical membership method, and then the membership of each fault mode is comprehensively obtained from the fault characteristics, so that the possibility that the motor is in each fault mode is obtained. Compared with the prior art, the method can obtain the fault characteristic membership function more timely through online monitoring, can quickly and comprehensively calculate the possibility that the motor is in each fault mode, is convenient to deploy the algorithm to the edge side or the cloud, and realizes the operation and maintenance of a large motor cluster.

Description

Motor fault diagnosis method
Technical Field
The invention relates to a motor fault diagnosis method, and belongs to the technical field of motor fault diagnosis and the technical field of motor operation and maintenance industry internet.
Background
The motor is a prime power of the manufacturing industry, is widely applied to industries and fields of metallurgy, petrifaction, chemical industry, coal, building, public facilities, household appliances and the like, is terminal energy utilization equipment with the largest power consumption, and is a target of high attention and key research on energy conservation and emission reduction. The motor consumes huge energy, is the heart of industrial equipment and is in the core position of the industrial equipment. The motor is a key core component of equipment in industries such as petroleum, coal, chemical industry, metallurgy, textile and the like, and particularly important service is interrupted once serious faults and unplanned shutdown occur. Many occasions of motor-driven equipment operation service need to ensure the continuity of operation, the fault stop cannot be tolerated, and the accidental fault of the motor can cause huge maintenance cost and associated loss, even cause casualties.
At present, the operation maintenance of the motor and the driving equipment is also passive maintenance, mainly post maintenance and preventive maintenance. The following maintenance cannot predict the accident shutdown, secondary damage, catastrophic consequences, high maintenance cost and out-of-control management. Preventive maintenance causes well-conditioned equipment to be overhauled frequently, damage from maintenance may be greater than the benefit of maintenance, unscheduled outages may still occur, and optimization and life analysis are not performed for different equipment. The current operation and maintenance mode reduces the production efficiency and improves the maintenance cost.
The current operation maintenance optimization based on the industrial internet is based on motor damage prediction on the use loss characteristic parameters, real-time monitoring and response are carried out on production equipment through the industrial internet technology, a predictive maintenance decision is made, and the service efficiency is improved. One important content is online real-time monitoring of the operation parameters of the motor, then according to a motor fault mechanism and a big data method, determining whether the motor is healthy, identifying a possible fault mode of the motor in a fault state, and providing timely and accurate reference information for operation and maintenance.
With the advance of industrial internet, data-driven motor fault diagnosis technology is rapidly developed at present and is used for obtaining a relation model between online monitoring data and various fault modes. After the relational models are obtained, the models need to be deployed to the edge side or the cloud, and online monitoring data are timely converted into the possibility that the motor is in various fault modes. At present, the problems of lack of a relation model between online monitoring data and various fault modes, lack of a fault diagnosis method based on the online monitoring data and the like exist.
Disclosure of Invention
The invention aims to solve the problem of fault diagnosis of the motor operation and maintenance industry internet and provides a motor fault diagnosis and display method based on online monitoring data.
In order to achieve the above object, a specific technical solution of the present invention is to provide a motor fault diagnosis method, which is characterized by comprising the following steps:
step 1, determining m fault modes and n fault characteristics of a motor;
step 2, establishing a relation matrix with sufficient conditions between the fault characteristics and the fault modes, and firstly assigning initial values as follows:
CF(i,j)＝0，i＝1～m，j＝1～n；
traversing i is 1 to m, j is 1 to n: when satisfying that the occurrence of the jth fault signature necessarily results in the occurrence of the ith fault mode, then:
CF(i,j)＝1；
step 3, establishing a relation matrix with necessary conditions between the fault characteristics and the fault modes, and assigning initial values as follows:
BY(i,j)＝0，i＝1～m，j＝1～n；
traversing i is 1 to m, j is 1 to n: when satisfying that the occurrence of the ith failure mode necessarily results in the occurrence of the jth failure characteristic, then:
BY(i,j)＝1；
step 4, obtaining a signal through monitoring the motor, and obtaining each fault characteristic array TZ (j) after comparing the signal with a preset characteristic requirement and a preset characteristic parameter, wherein j is 1-n, TZ (j) is a real number between 0 and 1 or-1, the real number between 0 and 1 represents the membership degree of the jth fault characteristic, and-1 represents that the fault characteristic is not monitored;
and 5, calculating to obtain a sufficient condition relation matrix CF1(i, j) under all known fault characteristic conditions:
traversing i is 1 to m, j is 1 to n: if tz (j) is-1, CF1(i, j) is 0, otherwise CF1(i, j) is CF (i, j) tz (j);
and 6, calculating to obtain a necessary condition relation matrix BY1(i, j) under all known fault characteristic conditions:
traversing i is 1 to m, j is 1 to n: if tz (j) is-1, BY1(i, j) is 1; otherwise: if BY (i, j) is 1, BY1(i, j) is TZ (j); if BY (i, j) is 0, BY1(i, j) is 1-TZ (j);
and 7, a membership array which is formed by integrating sufficient conditions and does not generate the fault mode in each fault mode is MS1 (i):
Figure BDA0002202553000000021
step 8, the membership array which is formed by integrating the necessary conditions of each fault mode and does not generate the mode is MS2 (i):
Figure BDA0002202553000000031
and 9, setting a comprehensive membership array of the fault characteristics corresponding to each fault mode as MS (i):
MS(i)＝1-MS1(i)·MS2(i)，i＝1～m；
and step 10, taking the serial number of the fault mode as an abscissa and the membership degree of the fault mode as an ordinate, and making a histogram of an MS (i) array.
Preferably, in step 4, the method for calculating the membership degree array tz (j) of the fault feature includes the following steps:
step 4.1, the time sequence of the motor monitoring parameters corresponding to the jth fault feature is as follows: d (j, k), k being 1 to k1，k1＝p·k2P is a positive integer, and the time interval of sampling the monitored parameter is t1；
Then, a group of data is formed according to each p continuous points for statistical analysis, and an average value sequence D of each group is obtainedav(j, r) and a sequence of standard deviations s (j, r), r being 1 to k2：
Figure BDA0002202553000000032
Figure BDA0002202553000000033
I.e. per p.t1The average value and the standard deviation of p sampling points in time;
step 4.2, when the motor normally runs, according to the method of the step 4.1, at k1·t1Obtaining a time sequence D (j, k) of each monitoring parameter corresponding to the motor fault characteristics within the monitoring time, and calculating to obtain Dav(j, r) and s (j, r), wherein k is 1 to k1、r＝1～k2；
At DavFinding the (j, r) sequence satisfying | s (j, r)/DavMinimum value D of (j, r) | < eav(j，r1) And maximum value Dav(j，r2) Where e is a given positive number, e.g. where e is 1, | s (j, r)/DavD of (j, r) | < eavThe standard deviation of the (j, r) sequence is smaller than the absolute value of the mean value thereof, and satisfies | s (j, r)/DavD of (j, r) | < eav(j, r) the sequences do not include sequences that deviate more from the average;
record subscript r1And r2And obtaining s (j, r)1) And s (j, r)2)；
Let D1＝Dav(j，r1)、D2＝Dav(j，r2)、s1＝s(j，r1)、s2＝s(j，r2)、
Figure BDA0002202553000000034
Figure BDA0002202553000000035
And 4.3, when the motor runs normally or in a fault and is monitored, acquiring a sequence D (j, k) of current p nearest time points of each monitoring parameter corresponding to the fault characteristics of the motor according to the method in the step 4.1, wherein k is 1-p, and calculating to obtain Dav(j,1) and s (j,1), let:
D＝Dav(j,1)
and solving the membership degree of the current monitoring parameter in a normal or fault state according to the following formula:
Figure BDA0002202553000000041
the membership degree TZ (j) of the fault characteristics adopts the following 4 different calculation methods according to different conditions during monitoring:
(1) the monitoring is in a normal running state, and the membership degree of the monitoring is higher than that of the normal characteristic:
Figure BDA0002202553000000042
(2) the monitoring is in a normal running state and is lower than the membership degree of normal characteristics:
Figure BDA0002202553000000043
(3) the monitoring is in a normal running state, and the membership degree of the normal characteristic is higher or lower than that of the normal characteristic:
TZ(j)＝1-v(j)
(4) the monitoring is a fault operation state, and belongs to the membership degree of the fault characteristics:
tz (j) v (j) step 4.4. for fault signatures that are not monitored, tz (j) is made-1.
According to the motor fault mechanism, the relation between the motor online monitoring data and the fault modes is established, the fault characteristics are obtained from the motor online monitoring data by adopting a fuzzy mathematical membership method, and then the membership of each fault mode is comprehensively obtained from the fault characteristics, so that the possibility that the motor is in each fault mode is obtained. Compared with the prior art, the method can obtain the fault characteristic membership function more timely through online monitoring, can quickly and comprehensively calculate the possibility that the motor is in each fault mode, is convenient to deploy the algorithm to the edge side or the cloud, and realizes the operation and maintenance of a large motor cluster.
Drawings
FIG. 1 is a bar graph of the MS (i) array.
Detailed Description
The embodiment discloses a motor fault diagnosis and display method, which comprises the following steps:
step 1, determining a fault mode and fault characteristics of a motor according to a motor fault mechanism; for example, the total number of failure modes shown in table 1 is m ═ 23; the total number of failure signatures shown in table 2 is n-8.
TABLE 1
Serial number Failure mode
01 Stator-rotor core misalignment
02 Loosening of stator terminal
03 Stator bottomLoosening of foot bolt
04 Stator-rotor mechanical contact
05 Non-uniformity of static air gap
06 Dynamic air gap non-uniformity
07 Axial play
08 Fastener release
09 Overspeed or underspeed
10 Stator current imbalance
11 Stator current overcurrent
12 Supply voltage over or under voltage
13 Out-of-limit power supply voltage frequency deviation
14 Three-phase unbalance of power supply voltage
15 Phase loss of power supply voltage
16 Insulation breakdown of stator core
17 Stator winding interphase short circuit
18 Stator winding turn-to-turn short circuit
19 Stator winding connection error
20 Dynamic balance overrun
21 Rotor broken bar
22 End ring damage
23 Rotor shaft flexure
TABLE 2
Figure BDA0002202553000000051
Step 2, establishing a relation matrix with sufficient conditions between the fault characteristics and the fault modes, and firstly assigning initial values as follows:
CF(i,j)＝0,i＝1～m,j＝1～n。
traversing i is 1 to m, j is 1 to n: when satisfying that the occurrence of the jth fault signature necessarily results in the occurrence of the ith fault mode, then
CF(i,j)＝1。
For example:
since the 2 nd fault signature "voltage unbalance is too high" necessarily results in the 14 th fault pattern "voltage three-phase unbalance", CF (14,2) ═ 1.
The contents of the final CF (i, j) array formed by integrating the relationships of all the sufficient conditions are as follows:
Figure BDA0002202553000000061
and 3, establishing a relation matrix with necessary conditions between the fault characteristics and the fault modes, and assigning initial values as follows:
BY(i,j)＝0,i＝1～m,j＝1～n。
traversing i is 1 to m, j is 1 to n: when the condition that the occurrence of the ith fault mode necessarily causes the occurrence of the jth fault characteristic is met, then
BY(i,j)＝1。
For example:
since the 2 nd failure mode "loose connector lug" will inevitably result in the 5 th failure feature "too high unbalance of current" and the 7 th failure feature "too large effective value of vibration", there are
BY(2,5)＝1；BY(2,7)＝1
The content of the BY (i, j) array is finally formed BY synthesizing the relations of all the necessary conditions as follows:
Figure BDA0002202553000000071
and 4, monitoring the motor to obtain signals, comparing the signals with preset characteristic requirements and characteristic parameters to obtain each fault characteristic array TZ (j), wherein j is 1-n, TZ (j) is a real number between 0 and 1 or a real number between-1, and the real number between 0 and 1 represents the membership degree of the jth fault characteristic, and-1 represents that the fault characteristic is not monitored. The fault characteristic array TZ (j) is obtained by the following steps:
step 4.1, the time sequence of the motor monitoring parameters corresponding to the jth fault feature is as follows: d (j, k), k being 1 to k1，k1＝p·k2P is a positive integer, and the time interval of sampling the monitored parameter is t1。
For example, take k1＝12000，k2＝1000，p＝12,t 110 seconds(s)
Then, a group of data is formed according to each p continuous points (120s) for statistical analysis, and an average value sequence D of each group is obtainedav(j, r) and a sequence of standard deviations s (j, r), r being 1 to k2：
Figure BDA0002202553000000081
Figure BDA0002202553000000082
I.e. the mean and standard deviation of 12 samples per 120 s.
Step 4.2, when the motor operates normally or in fault, acquiring the time sequence D (j, k) of each monitoring parameter corresponding to the fault characteristic of the motor within the monitoring time of 120000s, namely 2000min according to the method of the step 4.1, and calculating to obtain Dav(j, r) and s (j, r). Wherein k is 1 to 12000, and r is 1 to 1000.
At DavFinding the (j, r) sequence satisfying | s (j, r)/Dav(j,r)|<Minimum value of e Dav(j,r1) And maximum value Dav(j,r2) Where e is a given positive number. For example, | s (j, r)/D when e is 1av(j,r)|<e D ofavThe standard deviation of the (j, r) sequence is smaller than the absolute value of the mean value thereof, and satisfies | s (j, r)/Dav(j,r)|<e D ofavThe (j, r) sequence does not include a sequence that deviates from the average value in a large amount.
Record subscript r1And r2And obtaining s (j, r)1) And s (j, r)2)。
Order to
D1＝Dav(j,r1)
D2＝Dav(j,r2)
s1＝s(j,r1)
s2＝s(j,r2)
Figure BDA0002202553000000083
Figure BDA0002202553000000091
And 4.3, when the motor runs normally or in a fault and is monitored, acquiring a sequence D (j, k) of current nearest 12 time points of each monitoring parameter corresponding to the motor fault characteristic according to the method in the step 4.1, wherein k is 1-12, and calculating to obtain Dav(j,1) and s (j, 1). Order:
D＝Dav(j,1)
solving the membership degree of the current monitoring parameter in the normal state according to the following formula:
Figure BDA0002202553000000092
the membership degree TZ (j) of the fault characteristics adopts the following 4 different calculation methods according to different conditions of the fault:
(1) the monitoring is in a normal running state, and the membership degree of the monitoring is higher than that of the normal characteristic:
Figure BDA0002202553000000093
(2) the monitoring is in a normal running state and is lower than the membership degree of normal characteristics:
Figure BDA0002202553000000094
(3) the monitoring is in a normal running state, and the membership degree of the normal characteristic is higher or lower than that of the normal characteristic:
TZ(j)＝1-v(j)
(4) the monitoring is a fault operation state, and belongs to the membership degree of the fault characteristics:
TZ(j)＝v(j)
step 4.4. for failure characteristics not monitored, order
TZ(j)＝-1
For example, when the motor is in a 'rotor broken bar' fault, the fault characteristics are monitored by 2-8, and the TZ (j) is obtained through calculation as follows:
j 1 2 3 4 5 6 7 8
TZ(j) -1 0 0 1 0.5 0 0.98 0.95
and 5, calculating a sufficient condition relation matrix CF1(i, j) under all known fault characteristic conditions by the following procedure:
{
if tz (j) is-1, CF1(i, j) is 0;
otherwise CF1(i, j) ═ CF (i, j) · tz (j).
},i＝1～m,j＝1～n
The CF1(i, j) array content is as follows
Figure BDA0002202553000000101
And 6, calculating a necessary condition relation matrix BY1(i, j) under all known fault characteristic conditions BY the following program:
Figure BDA0002202553000000102
Figure BDA0002202553000000111
the BY1(i, j) array contents are as follows:
Figure BDA0002202553000000112
step 7. the membership array of each failure mode which is formed by synthesizing sufficient conditions and does not generate the failure mode is MS1(i),
Figure BDA0002202553000000113
step 8. the membership array of each failure mode which is synthesized by the necessary conditions and does not generate the mode is MS2(i),
Figure BDA0002202553000000121
step 9, the comprehensive membership degree array of the fault characteristics corresponding to each fault mode is MS (i),
MS(i)＝1-MS1(i)·MS2(i),i＝1～m
the following results are obtained through the calculation of the steps 7, 8 and 9:
i MS1(i) MS2(i) MS(i)
1 1 0.5345 0.4655
2 1 1 0
3 1 1 0
4 1 0.5345 0.4655
5 1 1 0
6 1 1 0
7 1 1 0
8 1 1 0
9 1 1 0
10 0.5 1 0.5
11 0 1 1
12 1 1 0
13 1 1 0
14 1 1 0
15 1 1 0
16 1 0.5345 0.4655
17 1 1 0
18 1 0.5345 0.4655
19 1 0.5345 0.4655
20 1 1 0
21 1 0.5345 0.4655
22 1 0.5345 0.4655
23 1 1 0
and step 10, taking the serial number of the fault mode as an abscissa and the membership degree of the fault mode as an ordinate, and making a histogram of an MS (i) array, such as the chart shown in FIG. 1. The failure mode with a large membership value can be displayed in the graph for the reference of operation and maintenance personnel.
In this embodiment, when the membership degrees of the four fault characteristics of "the effective value of current is too high", "the unbalance degree of current is too high", "the effective value of vibration is too high", and "the temperature is too high" are 1, 0.5, 0.98, and 0.95, the fault mode with the membership degree greater than 0.4 is obtained comprehensively: the stator and rotor current detection circuit comprises 9 modes of stator and rotor core misalignment, stator and rotor mechanical contact, stator current imbalance, stator current overcurrent, stator core insulation damage, stator winding turn-to-turn short circuit, stator winding connection error, rotor broken bar and end ring damage, wherein the membership degree of the stator current overcurrent reaches 1, and the reason is that the stator current overcurrent is directly explained by 'the current effective value is too high'.

Claims (2)

1. A motor fault diagnosis method is characterized by comprising the following steps:
step 1, determining m fault modes and n fault characteristics of a motor;
step 2, establishing a relation matrix with sufficient conditions between the fault characteristics and the fault modes, and firstly assigning initial values as follows:
CF(i，j)＝0，i＝1～m，j＝1～n；
traversing i is 1 to m, j is 1 to n: when satisfying that the occurrence of the jth fault signature necessarily results in the occurrence of the ith fault mode, then:
CF(i，j)＝1；
step 3, establishing a relation matrix with necessary conditions between the fault characteristics and the fault modes, and assigning initial values as follows:
BY(i，j)＝0，i＝1～m，j＝1～n；
traversing i is 1 to m, j is 1 to n: when satisfying that the occurrence of the ith failure mode necessarily results in the occurrence of the jth failure characteristic, then:
BY(i，j)＝1；
step 4, obtaining a signal through monitoring the motor, and obtaining a fault feature membership degree array TZ (j) after comparing the signal with a preset fault feature requirement and a preset fault feature parameter, wherein j is 1-n, TZ (j) is a real number between 0 and 1 or-1, the real number between 0 and 1 represents the membership degree of the jth fault feature, and-1 represents that the fault feature is not monitored;
and 5, calculating to obtain a sufficient condition relation matrix CF1(i, j) under all known fault characteristic conditions:
traversing i is 1 to m, j is 1 to n: if tz (j) is-1, CF1(i, j) is 0, otherwise CF1(i, j) is CF (i, j) tz (j);
and 6, calculating to obtain a necessary condition relation matrix BY1(i, j) under all known fault characteristic conditions:
traversing i is 1 to m, j is 1 to n: if tz (j) is-1, BY1(i, j) is 1; otherwise: if BY (i, j) is 1, BY1(i, j) is TZ (j); if BY (i, j) is 0, BY1(i, j) is 1-TZ (j);
and 7, a membership array which is formed by integrating sufficient conditions and does not generate the fault mode in each fault mode is MS1 (i):
Figure FDA0003013551890000011
step 8, the membership array which is formed by integrating the necessary conditions of each fault mode and does not generate the mode is MS2 (i):
Figure FDA0003013551890000021
and 9, setting a comprehensive membership array of the fault characteristics corresponding to each fault mode as MS (i):
MS(i)＝1-MS1(i)·MS2(i)，i＝1～m；
and step 10, taking the serial number of the fault mode as an abscissa and the membership degree of the fault mode as an ordinate, and making a histogram of an MS (i) array.
2. The motor fault diagnosis method according to claim 1, wherein in the step 4, the calculation method of the fault feature membership degree array tz (j) comprises the following steps:
step 4.1, the time sequence of the motor monitoring parameters corresponding to the jth fault feature is as follows: d (j, k), k being 1 to k1，k1＝p·k2P is a positive integer, and the time interval of sampling the monitored parameter is t1；
Then, a group of data is formed according to each p continuous points for statistical analysis, and an average value sequence D of each group is obtainedav(j, r) and a sequence of standard deviations s (j, r), r being 1 to k2：
Figure FDA0003013551890000022
Figure FDA0003013551890000023
Step 4.2, when the motor normally runs, according to the method of the step 4.1, at k1·t1Obtaining a time sequence D (j, k) of each monitoring parameter corresponding to the motor fault characteristics within the monitoring time, and calculating to obtain Dav(j, r) and s (j, r), wherein k is 1 to k1、r＝1～k2；
At DavFinding the (j, r) sequence satisfying | s (j, r)/DavMinimum value D of (j, r) | < eav(j，r1) And maximum value Dav(j，r2) E is a given positive number, recording the subscript r1And r2And obtaining s (j, r)1) And s (j, r)2)；
Let D1＝Dav(j，r1)、D2＝Dav(j，r2)、s1＝s(j，r1)、s2＝s(j，r2)、
Figure FDA0003013551890000024
Figure FDA0003013551890000025
And 4.3, when the motor runs normally or in a fault and is monitored, acquiring a sequence D (j, k) of current p nearest time points of each monitoring parameter corresponding to the fault characteristics of the motor according to the method in the step 4.1, wherein k is 1-p, and calculating to obtain Dav(j,1) and s (j,1), let:
D＝Dav(j，1)
and solving the membership degree of the current monitoring parameter in a normal or fault state according to the following formula:
Figure FDA0003013551890000026
the failure feature membership degree array TZ (j) of the failure features adopts the following 3 different calculation methods according to different conditions of failures:
(1) degree of membership above normal features:
Figure FDA0003013551890000031
(2) degree of membership lower than normal features:
Figure FDA0003013551890000032
(3) membership degree belonging to fault characteristics:
TZ(j)＝v(j)
step 4.4. for fault signatures that are not monitored, let tz (j) be-1.
CN201910870199.6A 2019-09-16 2019-09-16 Motor fault diagnosis method Active CN110554316B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910870199.6A CN110554316B (en) 2019-09-16 2019-09-16 Motor fault diagnosis method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910870199.6A CN110554316B (en) 2019-09-16 2019-09-16 Motor fault diagnosis method

Publications (2)

Publication Number Publication Date
CN110554316A CN110554316A (en) 2019-12-10
CN110554316B true CN110554316B (en) 2021-08-13

Family

ID=68740410

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910870199.6A Active CN110554316B (en) 2019-09-16 2019-09-16 Motor fault diagnosis method

Country Status (1)

Country Link
CN (1) CN110554316B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112684235B (en) * 2020-12-24 2024-02-23 浙江可胜技术股份有限公司 Online intelligent fault diagnosis method and system for speed reducer for heliostat
CN114301242B (en) * 2021-12-17 2023-08-04 安徽皖南新维电机有限公司 Mounting method suitable for mounting motor special for telescopic arm forklift

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011073613A1 (en) * 2009-12-15 2011-06-23 University Of Portsmouth A method, apparatus and computer program for diagnosing a mode of operation of a machine
CN103308855A (en) * 2013-05-29 2013-09-18 上海电机学院 Wind turbine generator system fault diagnosis method and device based on gray correlation
CN103994199A (en) * 2014-05-27 2014-08-20 中能电力科技开发有限公司 Gear case maintenance time determining method based on state monitoring
CN106153340A (en) * 2016-06-29 2016-11-23 北京工业大学 A kind of Fault Diagnosis of Roller Bearings
CN107490964A (en) * 2017-08-17 2017-12-19 杭州电子科技大学 A kind of rotating machinery fault feature reduction method of feature based evidence discretization
CN108107360A (en) * 2017-12-05 2018-06-01 中国电子产品可靠性与环境试验研究所 Electrical fault discrimination method and system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011073613A1 (en) * 2009-12-15 2011-06-23 University Of Portsmouth A method, apparatus and computer program for diagnosing a mode of operation of a machine
CN103308855A (en) * 2013-05-29 2013-09-18 上海电机学院 Wind turbine generator system fault diagnosis method and device based on gray correlation
CN103994199A (en) * 2014-05-27 2014-08-20 中能电力科技开发有限公司 Gear case maintenance time determining method based on state monitoring
CN106153340A (en) * 2016-06-29 2016-11-23 北京工业大学 A kind of Fault Diagnosis of Roller Bearings
CN107490964A (en) * 2017-08-17 2017-12-19 杭州电子科技大学 A kind of rotating machinery fault feature reduction method of feature based evidence discretization
CN108107360A (en) * 2017-12-05 2018-06-01 中国电子产品可靠性与环境试验研究所 Electrical fault discrimination method and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Multi-sensor data fusion using support vector machine for motor fault detection;Banerjee, Tribeni Prasad;《Information Sciences》;20121231;第217卷;第96-107页 *
电机故障诊断的多传感器数据融合方法;陈理渊 等;《电力系统及其自动化学报》;20050228;第17卷(第1期);第48-52页 *

Also Published As

Publication number Publication date
CN110554316A (en) 2019-12-10

Similar Documents

Publication Publication Date Title
Jin et al. Anomaly detection of cooling fan and fault classification of induction motor using Mahalanobis–Taguchi system
Pandarakone et al. Deep neural network based bearing fault diagnosis of induction motor using fast Fourier transform analysis
CN109765484A (en) Motor on-line monitoring and fault diagonosing method based on &#34; correct tree &#34; model
CN110554316B (en) Motor fault diagnosis method
He et al. Remote monitoring and diagnostics of pitch-bearing defects in an MW-scale wind turbine using pitch symmetrical-component analysis
CN112285562B (en) Asynchronous motor fault detection method based on electromagnetic field and thermal field multi-signal fusion
CN112541160B (en) Method for extracting related characteristics of vibration fault diagnosis of rotary machine
CN111008485A (en) Neural network-based multi-parameter life prediction method for three-phase alternating current asynchronous motor
Dash et al. Condition monitoring of induction motors:—A review
Leonidovich et al. The development and use of diagnostic systems and estimation of residual life in industrial electrical equipment
CN108872853B (en) Fault diagnosis method for high vibration of large steam turbine generator rotor
CN109214109B (en) Residual life prediction verification method for petrochemical equipment rotating machinery
Chang et al. Fuzzy theory-based partial discharge technique for operating state diagnosis of high-voltage motor
Refaat et al. Smart grid condition assessment: concepts, benefits, and developments
Domingues Industry 4.0 in maintenance: Using condition monitoring in electric machines
CN118060512A (en) Continuous casting machine control method, continuous casting machine control system and computer readable storage medium
Liu et al. Application of Frequency Domain Analysis Method in Vibration Analysis and Fault Diagnosis of Oil Transfer Pump Unit
Rosli et al. Application of principal component analysis vs. Multiple linear regression in resolving influential factor subject to air booster compressor Motor failure
CN115372039A (en) Construction method and application method of vibration fault diagnosis system of steam turbine generator unit
Lee et al. The Commercialization of Medium-Voltage Induction Motor Rotor Diagnostics Equipment: Helping Prevent In-Service Failures of Induction Motors and Processes
Szabo et al. Condition Monitoring for Detecting the Malfunction of Industrial Machines
Peng et al. [Retracted] Application of CNN‐Based Machine Learning in the Study of Motor Fault Diagnosis
Al-Leythi et al. Motor Watch-Motor Fault Signature Analysis
Li et al. Fault Diagnostic Opportunities for Electromagnetic Coils of Active Magnetic Bearings using Physics-of-Failure Analysis
Safonov et al. The predictive diagnosis method of electric drive state via an artificial neural network

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