CN113656977B - Coil fault intelligent diagnosis method and device based on multi-mode feature learning - Google Patents

Coil fault intelligent diagnosis method and device based on multi-mode feature learning Download PDF

Info

Publication number
CN113656977B
CN113656977B CN202110980867.8A CN202110980867A CN113656977B CN 113656977 B CN113656977 B CN 113656977B CN 202110980867 A CN202110980867 A CN 202110980867A CN 113656977 B CN113656977 B CN 113656977B
Authority
CN
China
Prior art keywords
coil
fault
mode
model
feature learning
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
CN202110980867.8A
Other languages
Chinese (zh)
Other versions
CN113656977A (en
Inventor
郭丽
张锐
李�杰
刘胜涛
***
王钤
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.)
Mianyang Weibo Electronic Co Ltd
Original Assignee
Mianyang Weibo Electronic 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 Mianyang Weibo Electronic Co Ltd filed Critical Mianyang Weibo Electronic Co Ltd
Priority to CN202110980867.8A priority Critical patent/CN113656977B/en
Publication of CN113656977A publication Critical patent/CN113656977A/en
Application granted granted Critical
Publication of CN113656977B publication Critical patent/CN113656977B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/04—Constraint-based CAD

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Algebra (AREA)
  • Computing Systems (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)

Abstract

The invention discloses a coil fault intelligent diagnosis method and device based on multi-mode feature learning, wherein the method comprises the following steps: acquiring multiple characteristic data information of a coil, wherein each characteristic data is used as data of one mode; constructing a multi-feature data sparse constraint model of the coil according to various feature data information of the coil; modeling the coil faults according to various characteristic data information of the coil to obtain a reconstruction fault model of the coil; according to the multi-feature data sparse constraint model of the coil and the reconstruction fault model of the coil, fusing the data processed by each mode to obtain a coil fault diagnosis model based on multi-mode feature learning, and solving the coil fault diagnosis model to obtain a fault E of the coil under a certain mode signal of the coil; and judging the fault reason of the coil according to the size of E. The invention improves the diagnosis accuracy of the coil faults, is not limited to the diagnosis of the sensor coil faults, and can be popularized and applied to motor coils, engine coils and the like.

Description

Coil fault intelligent diagnosis method and device based on multi-mode feature learning
Technical Field
The invention relates to the technical field of intelligent diagnosis of coil faults of a magnetic balance sensor, in particular to an intelligent diagnosis method and device of coil faults based on multi-mode feature learning.
Background
Since magnetic balance sensors are often used in complex and diverse industrial environments, various faults of the coil are inevitably generated during long-term continuous operation, under the influence of power supply conditions and load conditions. These faults can seriously affect the reliability and safety of the operation of the coil. If not diagnosed and repaired in a timely manner, they can lead to sensor damage, causing serious consumer damage and property damage.
Coil faults are various, but fall into two categories, one is electrical faults, such as current, voltage, frequency, power, and the like; the other is mechanical failure, loosening of the skeleton, falling off or breaking of the coil, turn-to-turn short circuit, etc. Often one pays attention to only one of the coil fault characteristics, for example only one of the current signal or the vibration signal is considered, but the coil will perform in many ways when it is faulty, this method is time consuming and there is a missing fault; the existing intelligent diagnosis method for the coil faults is low in performance and accuracy.
Disclosure of Invention
The invention aims to provide a coil fault intelligent diagnosis method and device based on multi-mode feature learning, which can extract information from the above possible factors as fault features for diagnosis (the invention uses the method for extracting current signals and vibration signal features for description), and provides a fault intelligent diagnosis method based on multi-mode feature learning and sparse representation.
The invention is realized by the following technical scheme:
in a first aspect, the present invention provides a coil fault intelligent diagnosis method based on multi-modal feature learning, the method comprising the steps of:
acquiring multiple characteristic data information of a coil, wherein each characteristic data is used as data of one mode;
constructing a multi-feature data sparse constraint model of the coil according to various feature data information of the coil; modeling the coil faults (data errors) according to various characteristic data information of the coil to obtain a reconstruction fault model of the coil;
according to the reconstruction fault model of the coil, fusing the data processed by each mode to obtain a coil fault diagnosis model objective function based on multi-mode feature learning; solving the coil fault diagnosis model objective function based on multi-mode feature learning to obtain a fault E of the coil under a certain mode signal of the coil; and judging the fault reason of the coil according to the size of E.
The fault reason of the coil is judged according to the size of E, and the fault judgment method comprises the following steps: e, e ij Representation ofThe ith row and jth column element in E, when
Figure BDA0003228955060000021
When the coil is in fault, the delta is the quality coefficient of the coil, and represents the coil quality, namely the anti-interference capability; to further determine what kind of failure is caused by the failure, the +.>
Figure BDA0003228955060000022
And when the fault is larger than 0, judging that the fault exists.
The working principle is as follows:
based on the problems of low diagnosis performance and low accuracy of the existing intelligent coil fault diagnosis method, the invention designs the intelligent magnetic balance sensor coil fault diagnosis method based on multi-mode feature learning of current signals, vibration signals and the like. The multi-mode signal processing method has not been applied to analysis and processing of electric signals such as current signals, vibration signals, voltage signals, and the like. For these electrical parameter signals, it is difficult for a single modality to provide complete information about noise interference during system operation. The multi-mode fusion mode can integrate characteristic information from different modes, draw the advantages of different modes and finish the integration of information. For the electric signals, the difficulty of fusing the extracted different mode features is that the feature signals are weak signals, and the feature differences are not obvious. For this case, we amplify the signal characteristics of the electrical signal as it is multi-modal processed. The multimodal fusion method of the present invention is shown in FIG. 2. The invention provides a specific method for extracting features before diagnosing a fault coil.
The intelligent diagnosis method for the coil faults based on multi-mode feature learning improves diagnosis performance and accuracy of the coil faults; the method is not limited to fault diagnosis of the sensor coil, and can be popularized and applied to motor coils, engine coils, transformer magnetic cores and the like.
Further, the plurality of characteristic data information of the coil comprises a current signal and a vibration signal of the coil.
Further, constructing a multi-feature data sparse constraint model of the coil according to various feature data information of the coil; the multi-feature data sparse constraint model of the coil is expressed as:
Figure BDA0003228955060000023
wherein D is (v) Features representing the v-th mode of the coil, D representing a matrix of m rows and n columns of feature signals,
Figure BDA0003228955060000024
λ 1 representing balance parameters for the sparse constraint term; I.I 1 Is the L1 norm, which represents the sparsity constraint; the principle of sparse representation theory is that a non-sparse original signal is converted into sparse coefficients through a dictionary matrix, and the sparse coefficients are used for representing the original signal. So sparse representation is also called sparse coding. The step is designed to reflect the essential characteristics of the sensor coil signal with a smaller data volume. Briefly, the sparse representation coefficients contain information of the original signal.
Further, modeling the coil faults (data errors) according to various characteristic data information of the coil to obtain a reconstruction fault model of the coil; the reconstructed fault model of the coil is expressed as:
Figure BDA0003228955060000031
wherein lambda is 2 Is that
Figure BDA0003228955060000032
Balance parameters of (2); e represents an error matrix of m rows and n columns, ">
Figure BDA0003228955060000033
E (v) Indicating a fault in the coil when the v-th mode signal is present.
Further, the objective function of the coil fault diagnosis model based on multi-modal feature learning is as follows:
Figure BDA0003228955060000034
wherein beta is (v) Adjusting parameters for each modality; d (D) (v) Characteristic of the v-th mode of the coil, D * Representing a matrix of m rows and n columns of characteristic signals,
Figure BDA0003228955060000035
λ 1 represents the balance parameters for the sparsity constraint terms, I.I 1 Is the L1 norm, which represents the sparsity constraint; e represents an error matrix of m rows and n columns, ">
Figure BDA0003228955060000036
E (v) A fault in the coil when representing the v-th mode signal; lambda (lambda) 2 Is->
Figure BDA0003228955060000037
Balance parameters of (2); s.t. represents constraint conditions, X (v) Indicating that the v-th modality signal was acquired.
Further, the objective function of the coil fault diagnosis model based on multi-mode feature learning is optimized and solved by adopting a Lagrange multiplier method.
In a second aspect, the present invention further provides a coil fault intelligent diagnosis device based on multi-mode feature learning, which is characterized in that the device supports the coil fault intelligent diagnosis method based on multi-mode feature learning, and the device includes:
the device comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring various characteristic data information of a coil, and the various characteristic data information of the coil comprises a current signal and a vibration signal of the coil; each characteristic data is used as data of one mode;
the multi-feature data sparse constraint model construction unit is used for constructing a multi-feature data sparse constraint model of the coil according to various feature data information of the coil;
the coil reconstruction fault model construction unit is used for modeling coil faults (data errors) according to various characteristic data information of the coil to obtain a coil reconstruction fault model;
the coil fault diagnosis model construction and solving unit is used for fusing the data processed by each mode according to the coil reconstruction fault model to obtain a coil fault diagnosis model objective function based on multi-mode feature learning; solving the coil fault diagnosis model objective function based on multi-mode feature learning to obtain a fault E of the coil under a certain mode signal of the coil;
the coil fault diagnosis unit is used for judging the fault reason of the coil according to the size of E, wherein the fault judgment method is as follows: e, e ij Represents the j-th element of the i-th row in E when
Figure BDA0003228955060000041
When the coil is in fault, the delta is the quality coefficient of the coil, and represents the coil quality, namely the anti-interference capability; to further determine what kind of failure is caused by the failure, the +.>
Figure BDA0003228955060000042
And when the fault is larger than 0, judging that the fault exists.
Further, the objective function of the coil fault diagnosis model based on multi-modal feature learning is as follows:
Figure BDA0003228955060000043
wherein beta is (v) Adjusting parameters for each modality; d (D) (v) Characteristic of the v-th mode of the coil, D * Representing a matrix of m rows and n columns of characteristic signals,
Figure BDA0003228955060000044
λ 1 represents the balance parameters for the sparsity constraint terms, I.I 1 Is the L1 norm, which represents the sparsity constraint; e represents an error matrix of m rows and n columns, ">
Figure BDA0003228955060000045
E (v) A fault in the coil when representing the v-th mode signal; lambda (lambda) 2 Is->
Figure BDA0003228955060000046
Balance parameters of (2); s.t. represents constraint conditions, X (v) Indicating that the v-th modality signal was acquired.
In a third aspect, the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the coil fault intelligent diagnosis method based on multi-modal feature learning when executing the computer program.
In a fourth aspect, the present invention further provides a computer readable storage medium, where a computer program is stored, where the computer program when executed by a processor implements the coil fault intelligent diagnosis method based on multi-modal feature learning.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the invention designs a magnetic balance sensor coil fault intelligent diagnosis method based on multi-mode feature learning of current signals, vibration signals and the like, and the invention considers that the signals have multiple modes, and applies the multi-mode signal processing method to analysis and processing of electric signals such as current signals, vibration signals, voltage signals and the like; the essential characteristics of the sensor coil signals are reflected through smaller data volume by utilizing sparse constraint, and after faults (such as turn-to-turn short circuits) occur, the amplitudes of signals such as current and vibration of the sensor coil signals are increased, harmonic waves (noise) occur, so that the fault cause of the sensor coil can be judged according to the size of the fault E of the coil by modeling the noise.
2. The invention designs an intelligent diagnosis method for coil faults of a magnetic balance sensor based on multi-mode feature learning such as current signals, vibration signals and the like, and improves the diagnosis accuracy of the coil faults; the method is not limited to fault diagnosis of the sensor coil, and can be popularized and applied to motor coils, engine coils, transformer magnetic cores and the like.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention. In the drawings:
FIG. 1 is a flow chart of a coil fault intelligent diagnosis method based on multi-modal feature learning.
FIG. 2 is a flow chart of the multi-modal fusion method of the present invention.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
The invention designs a magnetic balance sensor coil fault intelligent diagnosis method based on multi-mode feature learning of current signals, vibration signals and the like. The multi-mode signal processing method has not been applied to analysis and processing of electric signals such as current signals, vibration signals, voltage signals, and the like. For these electrical parameter signals, it is difficult for a single modality to provide complete information about noise interference during system operation. The multi-mode fusion mode can integrate characteristic information from different modes, draw the advantages of different modes and finish the integration of information. For the electric signals, the difficulty of fusing the extracted different mode features is that the feature signals are weak signals, and the feature differences are not obvious. For this case, we amplify the signal characteristics of the electrical signal as it is multi-modal processed. The multimodal fusion method of the present invention is shown in FIG. 2.
Example 1
As shown in FIG. 1, the invention provides a coil fault intelligent diagnosis method based on multi-mode feature learning, which is characterized in that a specific method for feature extraction is provided before a fault coil is diagnosed, the fault coil is firstly put in a vibrating table for power-on test, then a current signal and a vibration signal are respectively extracted from the fault coil, and finally fault model modeling and diagnosis analysis are carried out. The method comprises the following steps:
step 1: the method comprises the steps of acquiring various characteristic data information of a coil, wherein the characteristic data information mainly comprises a current signal and a vibration signal of the coil, and the characteristic data information can also comprise a voltage signal, a frequency signal, a power signal, an inter-turn short circuit signal and the like; each feature data is represented as D as data of one modality (v) Wherein D is (v) Features representing the v-th modality.
Step 2: constructing a multi-feature data sparse constraint model of the coil according to various feature data information of the coil, and realizing that the original signals of all modes are represented by the least elements; the multi-feature data sparse constraint model of the coil is expressed as:
Figure BDA0003228955060000061
wherein D is (v) Features representing the v-th mode of the coil, D representing a matrix of m rows and n columns of feature signals,
Figure BDA0003228955060000062
λ 1 represents the balance parameters for the sparsity constraint terms, I.I 1 Is the L1 norm, which represents the sparsity constraint; the principle of sparse representation theory is that a non-sparse original signal is converted into sparse coefficients through a dictionary matrix, and the sparse coefficients are used for representing the original signal. So sparse representation is also called sparse coding. The step is designed to reflect the essential characteristics of the sensor coil signal with a smaller data volume. Briefly, the sparse representation coefficients contain information of the original signal.
Step 3: modeling the coil faults (data errors) according to various characteristic data information of the coil to obtain a reconstruction fault model of the coil; the reconstructed fault model of the coil is expressed as:
Figure BDA0003228955060000063
wherein lambda is 2 Is that
Figure BDA0003228955060000064
Balance parameters of (2); e represents an error matrix of m rows and n columns, ">
Figure BDA0003228955060000065
E (v) Indicating a fault in the coil when the v-th mode signal is present.
Step 4: according to the reconstruction fault model of the coil, fusing the data processed by each mode to obtain a coil fault diagnosis model objective function based on multi-mode feature learning; solving the coil fault diagnosis model objective function based on multi-mode feature learning to obtain a fault E of the coil under a certain mode signal of the coil; and judging the fault reason of the coil according to the size of E. The design theory of the step 4 is that after faults (such as turn-to-turn short circuits) occur, according to theoretical research, the amplitudes of current and vibration of the faults are increased and harmonic waves (noise) occur, so that the fault reasons of the faults can be judged according to the size of E by modeling the noise of the faults.
The fault reason of the coil is judged according to the size of E, and the fault judgment method comprises the following steps: e, e ij Represents the j-th element of the i-th row in E when
Figure BDA0003228955060000066
When the coil is in fault, the delta is the quality coefficient of the coil, and represents the coil quality, namely the anti-interference capability; to further determine what kind of failure is caused by the failure, the +.>
Figure BDA0003228955060000067
And when the fault is larger than 0, judging that the fault exists.
Specifically, the objective function of the coil fault diagnosis model based on multi-modal feature learning is as follows:
Figure BDA0003228955060000068
wherein beta is (v) Adjusting parameters for each modality; d (D) (v) Features representing the v-th mode of the coil, D representing a matrix of m rows and n columns of feature signals,
Figure BDA0003228955060000071
λ 1 represents the balance parameters for the sparsity constraint terms, I.I 1 Is the L1 norm, which represents the sparsity constraint; e represents an error matrix of m rows and n columns, ">
Figure BDA0003228955060000072
E (v) A fault in the coil when representing the v-th mode signal; lambda (lambda) 2 Is->
Figure BDA0003228955060000073
Balance parameters of (a).
Equation (3) can be expressed as a lagrangian multiplier:
Figure BDA0003228955060000074
wherein, lambda 1 ,Λ 2 Is the Lagrangian multiplier and μ is the penalty factor for the Lagrangian term.
The solution process for company (4) is as follows:
I. update D (v) Regarding D (v) The sub-problems of (2) are as follows:
Figure BDA0003228955060000075
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure BDA0003228955060000076
can be derived from D (v) ＝UΣV T Wherein
Figure BDA0003228955060000077
Epsilon is H (v) Is composed of H (v) Singular value vectors after singular value decomposition.
II, update E (v) Regarding E (v) The sub-problems of (2) are as follows:
Figure BDA0003228955060000078
it can be derived that the process can be performed,
Figure BDA0003228955060000079
III, update S (v) Regarding S (v) The sub-problems of (2) are as follows:
Figure BDA0003228955060000081
it can be derived that the process can be performed,
Figure BDA0003228955060000082
IV. update D * Regarding D * The sub-problems of (2) are as follows:
Figure BDA0003228955060000083
it can be derived that the process can be performed,
Figure BDA0003228955060000084
to sum up, E is obtained.
The intelligent diagnosis method for the coil faults based on multi-mode feature learning improves diagnosis performance and accuracy of the coil faults; the method is not limited to fault diagnosis of the sensor coil, and can be popularized and applied to motor coils, engine coils, transformer magnetic cores and the like.
Example 2
As shown in fig. 1 to 2, the difference between the present embodiment and embodiment 1 is that the present embodiment provides a coil fault intelligent diagnosis device based on multi-modal feature learning, the device supports a coil fault intelligent diagnosis method based on multi-modal feature learning described in embodiment 1, the device includes:
the device comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring various characteristic data information of a coil, and the various characteristic data information of the coil comprises a current signal and a vibration signal of the coil; each characteristic data is used as data of one mode;
the multi-feature data sparse constraint model construction unit is used for constructing a multi-feature data sparse constraint model of the coil according to various feature data information of the coil;
the coil reconstruction fault model construction unit is used for modeling coil faults (data errors) according to various characteristic data information of the coil to obtain a coil reconstruction fault model;
the coil fault diagnosis model construction and solving unit is used for fusing the data processed by each mode according to the coil reconstruction fault model to obtain a coil fault diagnosis model objective function based on multi-mode feature learning; solving the coil fault diagnosis model objective function based on multi-mode feature learning to obtain a fault E of the coil under a certain mode signal of the coil;
the coil fault diagnosis unit is used for judging the fault reason of the coil according to the size of E, wherein the fault judgment method is as follows: e, e ij Represents the j-th element of the i-th row in E when
Figure BDA0003228955060000091
When the coil is in fault, the delta is the quality coefficient of the coil, and represents the coil quality, namely the anti-interference capability; to further determine what kind of failure is caused by the failure, the +.>
Figure BDA0003228955060000092
And when the fault is larger than 0, judging that the fault exists.
For further explanation of this embodiment, the multi-feature data sparsity constraint model of the coil is expressed as:
Figure BDA0003228955060000093
wherein D is (v) Features representing the v-th mode of the coil, D representing a matrix of m rows and n columns of feature signals,
Figure BDA0003228955060000094
λ 1 representing balance parameters for the sparse constraint term; I.I 1 Is the L1 norm, which represents the sparsity constraint.
For further explanation of the present embodiment, the reconstructed fault model of the coil is expressed as:
Figure BDA0003228955060000095
wherein lambda is 2 Is that
Figure BDA0003228955060000096
Balance parameters of (2); e represents an error matrix of m rows and n columns, ">
Figure BDA0003228955060000097
E (v) Indicating a fault in the coil when the v-th mode signal is present.
For further explanation of this embodiment, the objective function of the coil fault diagnosis model based on multi-modal feature learning is:
Figure BDA0003228955060000098
wherein beta is (v) Adjusting parameters for each modality; d (D) (v) Features representing the v-th mode of the coil, D representing a matrix of m rows and n columns of feature signals,
Figure BDA0003228955060000099
λ 1 represents the balance parameters for the sparsity constraint terms, I.I 1 Is the L1 norm, which represents the sparsity constraint; e (E) (v) A fault in the coil when representing the v-th mode signal; lambda (lambda) 2 Is->
Figure BDA00032289550600000910
Balance parameters of (a).
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims (7)

1. A coil fault intelligent diagnosis method based on multi-mode feature learning is characterized by comprising the following steps:
acquiring multiple characteristic data information of a coil, wherein each characteristic data is used as data of one mode;
constructing a multi-feature data sparse constraint model of the coil according to various feature data information of the coil; modeling the coil faults according to various characteristic data information of the coil to obtain a reconstruction fault model of the coil;
according to the reconstruction fault model of the coil, fusing the data processed by each mode to obtain a coil fault diagnosis model objective function based on multi-mode feature learning; solving the coil fault diagnosis model objective function based on multi-mode feature learning to obtain a fault E of the coil under a certain mode signal of the coil; judging the fault reason of the coil according to the size of E;
the multi-feature data sparse constraint model of the coil is expressed as:
Figure FDA0004270963130000011
wherein D is (v) Features representing the v-th mode of the coil, D representing a matrix of m rows and n columns of feature signals,
Figure FDA0004270963130000012
λ 1 representing balance parameters for the sparse constraint term; I.I 1 Is the L1 norm of the sample,which represents a sparse constraint;
the reconstructed fault model of the coil is expressed as:
Figure FDA0004270963130000013
wherein lambda is 2 Is that
Figure FDA0004270963130000014
Balance parameters of (2); e represents an error matrix of m rows and n columns, ">
Figure FDA0004270963130000015
E (v) A fault in the coil when representing the v-th mode signal;
the coil fault diagnosis model objective function based on multi-mode feature learning is as follows:
Figure FDA0004270963130000016
wherein beta is (v) Adjusting parameters for each modality; d (D) (v) Characteristic of the v-th mode of the coil, D * Representing a matrix of m rows and n columns of characteristic signals,
Figure FDA0004270963130000017
λ 1 represents the balance parameters for the sparsity constraint terms, I.I 1 Is the L1 norm, which represents the sparsity constraint; e represents an error matrix of m rows and n columns, ">
Figure FDA0004270963130000018
E (v) A fault in the coil when representing the v-th mode signal; lambda (lambda) 2 Is->
Figure FDA0004270963130000019
Balance parameters of (2); s.t. represents constraint conditions，X (v) Indicating that a v-th modal signal is acquired;
the fault reason of the coil is judged according to the size of E, and the fault judgment method is as follows: e, e ij Represents the j-th element of the i-th row in E when
Figure FDA0004270963130000021
When the coil is in fault, the coil is judged, delta is the quality coefficient of the coil, and the quality of the coil is represented; further calculate +.>
Figure FDA0004270963130000022
And when the voltage is larger than 0, judging that the coil is faulty due to the fault.
2. The intelligent diagnosis method for coil faults based on multi-mode feature learning according to claim 1, wherein the plurality of feature data information of the coil comprises a current signal and a vibration signal of the coil.
3. The intelligent coil fault diagnosis method based on multi-modal feature learning according to claim 1, wherein the coil fault diagnosis model objective function based on multi-modal feature learning is optimized and solved by using a lagrangian multiplier method.
4. A coil fault intelligent diagnosis apparatus based on multi-modal feature learning, characterized in that the apparatus supports a coil fault intelligent diagnosis method based on multi-modal feature learning as set forth in any one of claims 1 to 3, the apparatus comprising:
the device comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring various characteristic data information of a coil, and the various characteristic data information of the coil comprises a current signal and a vibration signal of the coil; each characteristic data is used as data of one mode;
the multi-feature data sparse constraint model construction unit is used for constructing a multi-feature data sparse constraint model of the coil according to various feature data information of the coil;
the coil reconstruction fault model construction unit is used for modeling the coil faults according to various characteristic data information of the coil to obtain a coil reconstruction fault model;
the coil fault diagnosis model construction and solving unit is used for fusing the data processed by each mode according to the coil reconstruction fault model to obtain a coil fault diagnosis model objective function based on multi-mode feature learning; solving the coil fault diagnosis model objective function based on multi-mode feature learning to obtain a fault E of the coil under a certain mode signal of the coil;
and the coil fault diagnosis unit is used for judging the fault reason of the coil according to the size of E.
5. The intelligent coil fault diagnosis device based on multi-modal feature learning according to claim 4, wherein the coil fault diagnosis model objective function based on multi-modal feature learning is:
Figure FDA0004270963130000023
wherein beta is (v) Adjusting parameters for each modality; d (D) (v) Characteristic of the v-th mode of the coil, D * Representing a matrix of m rows and n columns of characteristic signals,
Figure FDA0004270963130000024
λ 1 represents the balance parameters for the sparsity constraint terms, I.I 1 Is the L1 norm, which represents the sparsity constraint; e represents an error matrix of m rows and n columns, ">
Figure FDA0004270963130000025
E (v) A fault in the coil when representing the v-th mode signal; lambda (lambda) 2 Is->
Figure FDA0004270963130000026
Balance parameters of (2); s.t. represents constraint conditions, X (v) Indicating that the v-th modality signal was acquired.
6. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements a coil fault intelligent diagnosis method based on multi-modal feature learning as claimed in any one of claims 1 to 3 when executing the computer program.
7. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements a coil fault intelligent diagnosis method based on multi-modal feature learning as claimed in any one of claims 1 to 3.
CN202110980867.8A 2021-08-25 2021-08-25 Coil fault intelligent diagnosis method and device based on multi-mode feature learning Active CN113656977B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110980867.8A CN113656977B (en) 2021-08-25 2021-08-25 Coil fault intelligent diagnosis method and device based on multi-mode feature learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110980867.8A CN113656977B (en) 2021-08-25 2021-08-25 Coil fault intelligent diagnosis method and device based on multi-mode feature learning

Publications (2)

Publication Number Publication Date
CN113656977A CN113656977A (en) 2021-11-16
CN113656977B true CN113656977B (en) 2023-07-07

Family

ID=78481970

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110980867.8A Active CN113656977B (en) 2021-08-25 2021-08-25 Coil fault intelligent diagnosis method and device based on multi-mode feature learning

Country Status (1)

Country Link
CN (1) CN113656977B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114359660B (en) * 2021-12-20 2022-08-26 合肥工业大学 Multi-modal target detection method and system suitable for modal intensity change

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101340121A (en) * 2008-08-28 2009-01-07 湖北省电力试验研究院 Transient simulation simplified model for internal fault of generator, modeling method and application thereof
CN106441897A (en) * 2016-10-27 2017-02-22 石家庄铁道大学 Morphological component bearing failure diagnosis method based on dictionary study
KR20190072165A (en) * 2017-12-15 2019-06-25 주식회사 에이스이앤티 Fault diagnosis system of motor

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7592772B2 (en) * 2007-10-08 2009-09-22 University Of Victoria Innovation And Development Corporation Stator inter-turn fault detection of synchronous machines
CN104181460B (en) * 2014-07-07 2017-06-06 沈阳工业大学 A kind of permanent magnetic actuator vacuum circuit breaker method for diagnosing faults based on Multi-information acquisition
US10443530B1 (en) * 2018-05-22 2019-10-15 Gm Global Technology Operations Llc. System with solenoid assembly and method of fault diagnosis and isolation
CN110286279B (en) * 2019-06-05 2021-03-16 武汉大学 Power electronic circuit fault diagnosis method based on extreme tree and stack type sparse self-coding algorithm
CN112147494A (en) * 2020-07-10 2020-12-29 国网河北省电力有限公司雄安新区供电公司 Mechanical fault detection method for high-voltage vacuum circuit breaker
CN112345213A (en) * 2020-09-18 2021-02-09 华能河南中原燃气发电有限公司 Low-voltage direct-current circuit breaker mechanical fault diagnosis method
CN112132102B (en) * 2020-09-28 2024-04-19 天津工业大学 Intelligent fault diagnosis method combining deep neural network with artificial bee colony optimization
CN112926728B (en) * 2021-03-22 2022-09-06 南京理工大学 Small sample turn-to-turn short circuit fault diagnosis method for permanent magnet synchronous motor

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101340121A (en) * 2008-08-28 2009-01-07 湖北省电力试验研究院 Transient simulation simplified model for internal fault of generator, modeling method and application thereof
CN106441897A (en) * 2016-10-27 2017-02-22 石家庄铁道大学 Morphological component bearing failure diagnosis method based on dictionary study
KR20190072165A (en) * 2017-12-15 2019-06-25 주식회사 에이스이앤티 Fault diagnosis system of motor

Also Published As

Publication number Publication date
CN113656977A (en) 2021-11-16

Similar Documents

Publication Publication Date Title
CN110377984B (en) Industrial equipment residual effective life prediction method and system and electronic equipment
CN110442936B (en) Equipment fault diagnosis method, device and system based on digital twin model
Gao et al. ASM1D-GAN: An intelligent fault diagnosis method based on assembled 1D convolutional neural network and generative adversarial networks
CN113656977B (en) Coil fault intelligent diagnosis method and device based on multi-mode feature learning
CN112926728B (en) Small sample turn-to-turn short circuit fault diagnosis method for permanent magnet synchronous motor
CN110633870A (en) Harmonic early warning method, harmonic early warning device and terminal equipment
CN115617628A (en) Digital twin system, research and development method, equipment and storage medium
CN114036978A (en) Bearing fault diagnosis method and system based on Transformer and data enhancement
CN109359803B (en) Reliability evaluation method and device
CN102298333B (en) Controller hardware-in-the-loop simulation (HIL simulation) test apparatus used by automotive electrical power steering assembly
Wang et al. A probabilistic detectability-based structural sensor network design methodology for prognostics and health management
CN116522628A (en) Transformer fault diagnosis method and system based on mechanism and data driving
WO2022036689A1 (en) Method for fault diagnosis using a fault diagnosis model trained by virtual data
CN115329815A (en) Bearing fault diagnosis method and system for optimizing SVM (support vector machine) model parameters through bubble entropy and AOA (automated optical inspection)
CN113919388A (en) Electromechanical equipment fault diagnosis method and device integrating signal frequency spectrum amplitude modulation and deep learning
CN115270645B (en) Design method and system based on ERNIE-DPCNN model
US20240176318A1 (en) Computer-implemented method and device for predicting a state of a technical system
CN117267216B (en) Method and system for simulating and detecting hydraulic element model in ring working condition
Gandhi et al. System independent fault diagnosis for synchronous generator
Nguyen et al. Hardware Supported Data-Driven Modeling for ECU Function Development
CN114252810B (en) Transformer sound vibration fault monitoring method, system, equipment and readable storage medium
CN109066724B (en) Generator PSS model checking system
US20220413050A1 (en) Complicated system fault diagnosis method and system based on multi-stage model
CN114487819A (en) Dual-stator permanent magnet linear motor demagnetization fault diagnosis system and method
CN118070187A (en) Fault diagnosis method, equipment and medium for oil immersed transformer

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