KR20220141019A - Method and apparatus for diagnosis of motor using current signals - Google Patents

Abstract

A method for diagnosing a motor failure according to the present invention comprises the steps of: learning a neural network model using learning data obtained from a phase current signal of a motor, wherein the neural network model includes a failure diagnosis module for identifying a failure mode of the motor and each failure mode and a severity estimation module for estimating a failure severity level of the failure mode, and feature data extracted from the failure diagnosis module is input to the severity estimation module; and determining a failure mode and failure severity level of the motor using the learned neural network model.

Description

Method and apparatus for diagnosis of motor failure using phase current signals

The present invention relates to a method and apparatus for diagnosing a motor failure, and more particularly, to a method and apparatus for diagnosing a motor failure capable of identifying a failure mode of a motor and estimating a failure severity using a phase current signal.

Motors are widely used in various applications where torque is required due to their low cost and high reliability. Motors are subject to mechanical and electrical failures because they are exposed to unexpected stresses such as damage and environmental conditions during use. Since the deterioration of motor performance leads to deterioration of product quality, it is important to diagnose the condition of the motor and evaluate the severity of the failure.

Existing techniques for diagnosing machine failures using deep learning mainly use vibration signals. In the case of motors, an additional sensor is required to measure vibration signals, so a fault diagnosis technique using a phase current signal that is easy to measure versus a vibration signal is being studied. has been

Existing motor fault diagnosis technology using a phase current signal analyzes a signal frequency or diagnoses a motor fault by processing a signal based on a large amount of data or a fuzzy method. In addition, most of the existing techniques for estimating the severity of motor failures are limited to observing changes in the health factor according to the level of failure. However, in order to know the failure characteristic frequency, prior knowledge about the motor (eg, number of poles, bearing information, etc.) is required, and the signal processing-based method also requires considerable expert knowledge because parameters must be selected based on experience. . In addition, there are many cases where the health factors of the related art overlap with each other despite the different types of failures, so it is difficult to apply them in practice.

An object of the present invention is to provide a motor failure diagnosis method and apparatus capable of identifying a failure mode of a motor and estimating a failure severity through a deep learning model using a phase current signal.

Motor failure diagnosis method according to the present invention for solving the above technical problem, the step of learning a neural network model using learning data obtained from a phase current signal of a motor - Here, the neural network model is a failure to identify a failure mode of the motor a diagnosis module and a severity estimation module for estimating a failure severity for each failure mode, wherein feature data extracted from the failure diagnosis module is input to the severity estimation module; and determining a failure mode and failure severity of the motor using the learned neural network model.

The severity estimation module may be provided to correspond to each failure mode, and the characteristic data may be input to the severity estimation module corresponding to the failure mode identified through the failure diagnosis module.

The failure diagnosis module may include a plurality of sequentially connected convolution blocks, and the characteristic data output from the last convolution block may be input to the failure severity module. Each of the plurality of convolution blocks may include a convolution layer and a pooling layer. The failure diagnosis module may further include a fully connected layer that is connected to the last convolution block and outputs a failure mode.

The severity estimation module may include a plurality of sequentially connected convolution blocks and a fully connected layer connected to the last convolution block to output a failure severity. Each of the plurality of convolution blocks may include a convolution layer and a pooling layer.

The motor failure diagnosis method may further include generating the learning data by pre-processing the phase current signal.

The learning includes learning the failure diagnosis module using the input data and then learning the severity estimation module using the characteristic data, and applying the characteristic data extracted from the learned failure diagnosis module to the failure mode. By inputting the corresponding severity estimation module, the severity estimation module may be trained.

In the learning step, the failure diagnosis module and the severity estimation module are simultaneously learned, and the characteristic data extracted from the failure diagnosis module during the learning process is input to the severity estimation module corresponding to the failure mode, and the severity estimation module is executed. can learn

Motor failure diagnosis apparatus according to the present invention for solving the above technical problem, a learning unit for learning a neural network model using learning data obtained from a phase current signal of a motor - Here, the neural network model is to identify a failure mode of the motor a failure diagnosis module and a severity estimation module for estimating failure severity for each failure mode, wherein feature data extracted from the failure diagnosis module is input to the severity estimation module; and a determination unit for determining a failure mode and a failure severity of the motor using the learned neural network model.

The motor failure diagnosis apparatus may further include a preprocessor configured to preprocess the phase current signal to generate the learning data.

The learning unit learns the failure diagnosis module by using the learning data and then learns the severity estimation module using the characteristic data, and uses the characteristic data extracted from the learned failure diagnosis module to correspond to the failure mode. By inputting into the severity estimation module, the severity estimation module may be trained.

In the learning step, the failure diagnosis module and the severity estimation module are simultaneously learned, and the characteristic data extracted from the failure diagnosis module during the learning process is input to the severity estimation module corresponding to the failure mode, and the severity estimation module is executed. can learn

According to the present invention described above, it is possible to diagnose a motor failure and estimate the failure severity through a deep learning model using a phase current signal that does not require installation of an additional sensor and is easily acquired.

In addition, motor failure diagnosis and severity estimation can be performed through a deep learning model without professional knowledge such as motor-related characteristic information or complex signal processing technology.

In addition, the feature data extracted from the upper module that identifies the failure mode is utilized to learn the lower module for estimating the failure severity, so that the failure-related features extracted from the upper module are efficiently reused, through which the lower module learns from the upper module Based on the obtained information, only the characteristics according to the corresponding failure mode can be intensively learned, so that the severity estimation performance can be improved.

1 is a block diagram of an apparatus for diagnosing a motor failure according to an embodiment of the present invention.
2 shows a schematic structure of a neural network model for diagnosing a motor failure and estimating the severity of a failure according to an embodiment of the present invention.
3 shows a detailed structure of a neural network model for diagnosing a motor failure and estimating the severity of a failure according to an embodiment of the present invention.
4 shows an example of a feature space in which feature data extracted from the first to third convolution blocks of the fault diagnosis module are visualized using t-SNE.
5 is a flowchart of a neural network model training process according to an embodiment of the present invention.
6 is a flowchart of a neural network model training process according to another embodiment of the present invention.
7 is a flowchart illustrating a motor failure diagnosis or neural network model testing process according to an embodiment of the present invention.
FIG. 8 shows the error diagnosis accuracy and severity estimation error of the failure diagnosis and severity estimation results of the embodiment of the present invention and the conventional technique.
9 is a bar graph showing the severity estimation error of the embodiment of the present invention and the conventional technique.
10 shows a comparison of the severity estimation performance of an embodiment of the present invention and an existing technique.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings. In the following description and the accompanying drawings, substantially the same components are denoted by the same reference numerals, so that redundant descriptions will be omitted. In addition, in the description of the present invention, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the gist of the present invention, a detailed description thereof will be omitted.

1 is a block diagram of an apparatus for diagnosing a motor failure according to an embodiment of the present invention. The motor failure diagnosis apparatus according to the present embodiment may include a preprocessor 110 , a learning unit 120 , a neural network model 130 , and a determination unit 140 .

The preprocessor 110 preprocesses the phase current signal of the motor to generate learning data or input data.

The phase current signal may be measured by installing an AC current sensor in the power supply of the motor, or may be measured from an output terminal of a current controller inside a control device that drives the motor. Pre-processing may include resampling, augmentation, normalization, scaling, and the like. Resampling is a process of uniformly matching the sampling rate because the training accuracy may drop when the sampling rates of the acquired phase current signals are different. Augmentation is a process of increasing the amount of data in deep learning model training because the more training data, the better the accuracy. Normalization is a process of equalizing data, and scaling is a process to secure the possibility of extending application to motors with different capacities or different driving environments.

The learning unit 120 trains the neural network model 130 that outputs the failure mode and the failure severity for the failure mode by using the learning data, which is data obtained by preprocessing the phase current signal.

2 shows a schematic structure of a neural network model 130 for diagnosing a motor failure and estimating the severity of a failure according to an embodiment of the present invention.

The neural network model 130 includes a failure diagnosis module 200 for identifying a failure mode of the motor as an upper module, and a severity estimation module 300, 400, and 500 for estimating the failure severity for each failure mode as a lower module. can do.

The failure mode may include Normal and a plurality of failure types (Fault 1, 2, 3). Although three failure types are exemplified in this embodiment, the failure types may be any number of one or more. For example, the failure type of the motor may include eccentricity, damage to the rotor rod, imbalance, and the like.

The severity estimation modules 300 , 400 , and 500 may be provided to correspond to each failure mode (failure type). For example, the first to third severity estimation modules 300 , 400 , and 500 may be provided to respectively correspond to the failure types ( Fault 1 , 2 , and 3 ). The first severity estimation module 300 outputs the fault severity for Fault 1, the second severity estimation module 400 outputs the fault severity for Fault 2, and the third severity estimation module 500 outputs the fault severity for Fault 3. It is possible to output the failure severity for In this embodiment, three severity estimation modules 300 , 400 , and 500 corresponding to three failure types are exemplified, but the severity estimation module may also be any number of one or more according to the number of failure types.

The feature data extracted from the failure diagnosis module 200 may be input to the severity estimation module corresponding to the failure mode identified through the failure diagnosis module 200 . That is, when Fault 1 is identified through the fault diagnosis module 200 , the characteristic data is input to the first severity estimation module 300 , and when Fault 2 is identified through the fault diagnosis module 200 , the characteristic data is estimated as the second severity It is input to the module 400 , and when Fault 3 is identified through the fault diagnosis module 200 , the characteristic data may be input to the third severity estimation module 500 . Accordingly, the first to third severity estimating modules 300 , 400 , and 500 may estimate the failure severity for each of the failure types Fault 1 , 2 , and 3 .

The learning data may be learned as a health factor indicating a failure characteristic while passing through the failure diagnosis module 200 . The severity estimation module 300 , 400 , 500 uses, as an input, not the input data used in the failure diagnosis module 200 , but the characteristic data (ie, latent characteristic) extracted from the failure diagnosis module 200 as an input to a specific type of failure You can focus on learning only the severity of The failure severity is set as a continuous value rather than a discrete value, so that the severity estimation modules 300 , 400 , and 500 may be designed to be utilized as a failure prediction regression model in the future.

로 표현될 수 있다. 여기서

는 고장 모드를, x는 입력 데이터(학습 데이터)를, W_FD는 고장 진단 모듈(200)의 웨이트(파라미터) 매트릭스를 나타낸다. 즉, 고장 진단 모듈(200)은 입력 데이터 x가 고장 진단 모듈(200)을 통과하여 진단된 고장 모드(

)가 실제 고장 모드(

)와 유사하도록 손실함수를 최소화하는 방향으로 학습될 수 있다. 고장 진단 모듈(200)의 손실함수

는 크로스-엔트로피(cross-entropy)를 이용하여 계산될 수 있고, 예를 들어 다음과 같이 표현될 수 있다.The task of the fault diagnosis module 200 is

can be expressed as here

is a failure mode, x is input data (learning data), and W _FD is a weight (parameter) matrix of the failure diagnosis module 200 . That is, the failure diagnosis module 200 is a failure mode (

) is the actual failure mode (

) can be learned in the direction of minimizing the loss function. Loss function of the fault diagnosis module 200

may be calculated using cross-entropy, and may be expressed, for example, as follows.

Here, β ₁ represents the L2 normalization coefficient.

로 표현될 수 있다. 여기서

는 고장 진단 모듈(200)에서 추출된 특징 데이터를, W_SE는 심각도 추정 모듈의 웨이트(파라미터) 매트릭스를, S는 고장 심각도를 나타낸다. 고장 진단 모듈(200)의 손실함수가 충분히 감소한 경우, 특징 데이터

는 특정 고장에 대한 충분한 정보를 담고 있기 때문에 심각도 추정 모듈(W_SE)의 학습 시 특정 고장의 심각도에 집중된 학습이 가능하다. 심각도 추정 모듈은 특징 데이터

가 해당 심각도 추정 모듈(W_SE)을 통과하여 추정된 특정 고장의 심각도(

)가 실제 고장 심각도(

)와 유사하도록 손실함수를 최소화하는 방향으로 학습될 수 있다. 심각도 추정 모듈의 손실함수

는 제곱평균오차(MSE)를 이용하여 계산될 수 있고, 예를 들어 다음과 같이 표현될 수 있다.The severity estimating modules 300 , 400 , and 500 are provided for each failure mode, so that a specific severity estimating module can be learned according to the failure mode identification result of the failure diagnosis module 200 , which is an upper module. The task of the severity estimation module is

can be expressed as here

is the feature data extracted from the fault diagnosis module 200, W _SE is the weight (parameter) matrix of the severity estimation module, and S is the fault severity. When the loss function of the fault diagnosis module 200 is sufficiently reduced, characteristic data

Since W SE contains sufficient information about a specific fault, it is possible to focus on the severity of a specific fault when learning the severity estimation module (W _SE ). The severity estimation module uses the feature data

is passed through the corresponding severity estimation module (W _SE ) and estimated the severity (

) is the actual failure severity (

) can be learned in the direction of minimizing the loss function. Severity Estimation Module's Loss Function

may be calculated using the mean square error (MSE), and may be expressed, for example, as follows.

및 심각도 추정 모듈의 W_SE로부터 계산된 심각도를 나타낸다. where β ₂ represents the L2 regularization coefficient, and f ₂ is the feature data

and the severity calculated from W _SE of the severity estimation module.

3 shows a detailed structure of a neural network model for diagnosing a motor failure and estimating the severity of a failure according to an embodiment of the present invention.

The failure diagnosis module 200 includes a plurality of sequentially connected convolution blocks 210 , 220 , 230 and a fully connected layer connected to the last convolution block 230 and outputting a failure mode ( 240) may be included. In this embodiment, the number of convolution blocks is three as an example, but the number of convolution blocks may be one or more arbitrary numbers. Each of the convolution blocks 210 , 220 , and 230 may include convolutional layers 211 , 221 , 231 and pooling layers 212 , 222 , and 232 .

4 shows an example of a feature space in which feature data extracted from the first to third convolution blocks 210 , 220 , and 230 of the fault diagnosis module 200 are visualized using t-SNE.

Referring to FIG. 4 , it can be seen that the feature space of the third convolution block 230 forms a more condensed cluster with respect to the failure mode compared to the first and second convolution blocks 210 and 220 . Based on the fact that the degree of failure characteristic learning increases as it passes through the convolution block as described above, the characteristic data output from the last convolution block 230 of the failure diagnosis module 200 is used as input data of the severity estimation module 300 , 400 , and 500 . can be used as However, according to an embodiment, feature data output from an arbitrary convolution block of the fault diagnosis module 200 may be used as input data.

Referring back to FIG. 3, each severity estimation module 300, 400, 500 includes a plurality of sequentially connected convolution blocks [(310, 320), (410, 420), (510, 520)] and, It may include fully connected layers 330 , 430 , 530 that are connected to the last convolution blocks 320 , 420 , and 520 and output the failure severity. In this embodiment, the number of convolution blocks is two as an example, but the number of convolution blocks may be one or more arbitrary numbers. Each convolutional block [(310, 320), (410, 420), (510, 520)] consists of a convolutional layer [(311, 321), (411, 421), (511, 521)] and a pooling layer ( pooling layer) [(312, 322), (412, 422), (512, 522)].

Referring back to FIG. 1 , the determination unit 140 inputs the pre-processed input data of the phase current signal to the learned neural network model 130 when testing the neural network model 130 or diagnosing the motor to cause motor failure. Mode and fault severity can be determined. For example, when the input data is classified as Fault 1 through the fault diagnosis module 200, the feature data extracted from the fault diagnosis module 200 is input to the first severity estimation module 300 corresponding to Fault 1, and the first The severity of Fault 1 may be estimated through the severity estimation module 300 .

5 is a flowchart of a learning process of the neural network model 130 according to an embodiment of the present invention. In this embodiment, the failure diagnosis module 200 is learned using the learning data and then the severity estimation modules 300, 400, and 500 are learned using the characteristic data of the failure diagnosis module 200, and the learned failure diagnosis is performed. By inputting the feature data extracted from the module 200 into the severity estimation module corresponding to the corresponding failure mode, the severity estimation module is trained.

When the phase current signal labeled with the failure mode and the failure severity is prepared (step 510), the preprocessor 110 preprocesses the phase current signal to generate learning data (step 515).

)를 계산한다(525단계). 530단계에서 학습이 완료되지 않았으면, 학습부(120)는 고장 진단 모듈(200)의 그래디언트를 계산하고 파라미터(W_FD)를 업데이트(535단계)한 다음, 520단계로 돌아가 학습을 반복한다. 이러한 학습 과정은 미니 배치 경사 하강법(mini-batch gradient descent method)으로 수행될 수 있다.The learning unit 120 inputs the learning data to the failure diagnosis module 200 (step 520), and the loss function (

) is calculated (step 525). If the learning is not completed in step 530, the learning unit 120 calculates the gradient of the fault diagnosis module 200, updates the parameter W _FD (step 535), and then returns to step 520 to repeat the learning. This learning process may be performed by a mini-batch gradient descent method.

)를 계산한다(555단계). 560단계에서 학습이 완료되지 않았으면, 학습부(120)는 해당 심각도 추정 모듈의 그래디언트를 계산하고 파라미터(W_SE)를 업데이트(565단계)한 다음, 550단계로 돌아가 학습을 반복한다. 이러한 학습 과정 역시 미니 배치 경사 하강법(mini-batch gradient descent method)으로 수행될 수 있다. 530단계에서 심각도 추정 모듈의 학습이 완료되면 종료한다.When the learning of the failure diagnosis module 200 is completed in step 530, the learning unit 120 inputs the learning data to the learned failure diagnosis module 200 (step 540), and features data from the failure diagnosis module 200 Extract (step 545). The learning unit 120 inputs the characteristic data to the severity estimation module corresponding to the failure mode identified through the failure diagnosis module 200 (step 550), and a loss function (

) is calculated (step 555). If the learning is not completed in step 560, the learning unit 120 calculates the gradient of the corresponding severity estimation module, updates the parameter W _SE (step 565), and then returns to step 550 to repeat the learning. This learning process may also be performed by a mini-batch gradient descent method. When the learning of the severity estimation module is completed in step 530, it ends.

6 is a flowchart of a learning process of the neural network model 130 according to another embodiment of the present invention. In this embodiment, the failure diagnosis module 200 and the severity estimation module 300, 400, and 500 are simultaneously learned, and the characteristic data extracted from the failure diagnosis module 200 during the learning process is used to estimate the severity corresponding to the failure mode. Enter the module to train the severity estimation module.

When the phase current signal labeled with the failure mode and the failure severity is prepared (step 610), the preprocessor 110 preprocesses the phase current signal to generate learning data (step 615).

)를 계산한다(625단계). 학습부(120)는 고장 진단 모듈(200)에서 특징 데이터를 추출하여(630단계), 특징 데이터를 고장 진단 모듈(200)을 통해 식별된 고장 모드에 대응하는 심각도 추정 모듈에 입력하고(635단계), 해당 심각도 추정 모듈의 손실함수(

)를 계산한다(640단계). 645단계에서 학습이 완료되지 않았으면, 학습부(120)는 고장 진단 모듈(200)과 심각도 추정 모듈의 그래디언트를 계산하고 파라미터(W_FD, W_SE)를 업데이트(650단계)한 다음, 620단계로 돌아가 학습을 반복한다. 이러한 학습 과정 역시 미니 배치 경사 하강법(mini-batch gradient descent method)으로 수행될 수 있다. 645단계에서 학습이 완료되면 종료한다. The learning unit 120 inputs the learning data to the failure diagnosis module 200 (step 620), and the loss function (

) is calculated (step 625). The learning unit 120 extracts the characteristic data from the failure diagnosis module 200 (step 630), and inputs the characteristic data to the severity estimation module corresponding to the failure mode identified through the failure diagnosis module 200 (step 635) ), the loss function of the corresponding severity estimation module (

) is calculated (step 640). If the learning is not completed in step 645, the learning unit 120 calculates the gradients of the fault diagnosis module 200 and the severity estimation module, and updates the parameters (W _FD , W _SE ) (step 650), and then, in step 620 Return to repeat the learning. This learning process may also be performed by a mini-batch gradient descent method. When the learning is completed in step 645, it ends.

7 is a flowchart illustrating a motor failure diagnosis or testing process of the neural network model 130 according to an embodiment of the present invention.

The preprocessor 110 preprocesses the phase current signal to generate input data (step 710). In this case, the pre-processing may include resampling, normalization, and scaling.

The determination unit 140 inputs the input data to the failure diagnosis module 200 (step 720), and identifies a failure mode through the failure diagnosis module 200 (step 730). The determination unit 140 extracts feature data from the failure diagnosis module 200 (step 740), and inputs the extracted feature data to the severity estimation module corresponding to the failure mode identified in step 730 (step 750) , the severity of the failure mode is estimated through the corresponding severity estimation module (step 760).

8 shows the error diagnosis accuracy and severity estimation error of the failure diagnosis and severity estimation results of the embodiment of the present invention and the existing technique, and FIG. 9 is a bar graph expressing the severity estimation error of the embodiment of the present invention and the existing technique. . Existing technique 1 uses spectral features and a machine learning classifier, and it uses the frequency magnitude of the fault characteristic of the phase current signal as a soundness factor to learn a support vector machine to diagnose the fault and estimate the severity. did. Existing technique 2 uses principal component analysis and a machine learning classifier. It extracts soundness factors from the frequency magnitude of the phase current signal through Principal Component Analysis (PCA) and trains a support vector machine to diagnose and perform malfunctions. Severity estimation was performed. Referring to FIG. 8 , the fault diagnosis accuracy in the embodiment of the present invention is higher than that of the existing technique by 2% or more, and in particular, referring to FIG. It can be seen that the improvement is approx.

10 shows a comparison of the severity estimation performance of an embodiment of the present invention and an existing technique. Referring to FIG. 10 , it can be seen that the failure severity estimation results of the embodiment of the present invention in all failure types of eccentricity, rotor rod damage, and imbalance appear much closer to the actual failure severity compared to the conventional technique.

A device according to embodiments of the present invention includes a processor, a memory for storing and executing program data, a permanent storage such as a disk drive, a communication port for communicating with an external device, a touch panel, a key, and a button user interface devices, such as, and the like. Methods implemented as software modules or algorithms may be stored on a computer-readable recording medium as computer-readable codes or program instructions executable on the processor. Here, the computer-readable recording medium includes a magnetic storage medium (eg, read-only memory (ROM), random-access memory (RAM), floppy disk, hard disk, etc.) and an optically readable medium (eg, CD-ROM). ), DVD (Digital Versatile Disc), and the like. The computer-readable recording medium is distributed among network-connected computer systems, so that the computer-readable code can be stored and executed in a distributed manner. The medium may be readable by a computer, stored in a memory, and executed on a processor.

Embodiments of the present invention may be represented by functional block configurations and various processing steps. These functional blocks may be implemented in any number of hardware and/or software configurations that perform specific functions. For example, an embodiment may be an integrated circuit configuration, such as memory, processing, logic, look-up table, etc., capable of executing various functions by means of the control of one or more microprocessors or other control devices. can be hired Similar to how the components of the present invention may be implemented as software programming or software components, embodiments may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, including C, C++ , Java, assembler, etc. may be implemented in a programming or scripting language. Functional aspects may be implemented in an algorithm running on one or more processors. Further, embodiments may employ prior art techniques for electronic configuration, signal processing, and/or data processing, and the like. Terms such as “mechanism”, “element”, “means” and “configuration” may be used broadly and are not limited to mechanical and physical configurations. The term may include the meaning of a series of routines of software in connection with a processor or the like.

The specific implementations described in the embodiment are only embodiments, and do not limit the scope of the embodiment in any way. For brevity of the specification, descriptions of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connections or connecting members of the lines between the components shown in the drawings exemplify functional connections and/or physical or circuit connections, and in an actual device, various functional connections, physical connections that are replaceable or additional may be referred to as connections, or circuit connections. In addition, unless there is a specific reference such as "essential", "importantly", etc., it may not be a necessary component for the application of the present invention.

So far, with respect to the present invention, the preferred embodiments have been looked at. Those of ordinary skill in the art to which the present invention pertains will understand that the present invention may be implemented in a modified form without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments are to be considered in an illustrative rather than a restrictive sense. The scope of the present invention is indicated in the claims rather than the foregoing description, and all differences within the scope equivalent thereto should be construed as being included in the present invention.

Claims (20)

A method for diagnosing a motor failure, comprising:
Training a neural network model using the learning data obtained from the phase current signal of the motor, wherein the neural network model includes a failure diagnosis module for identifying a failure mode of the motor and a severity estimation module for estimating the failure severity for each failure mode and inputting the feature data extracted from the fault diagnosis module into the severity estimation module; and
and determining a failure mode and a failure severity of the motor using the learned neural network model. According to claim 1,
The severity estimation module is provided to correspond to each failure mode,
The motor failure diagnosis method, characterized in that the characteristic data is input to a severity estimation module corresponding to the failure mode identified through the failure diagnosis module. According to claim 1,
The failure diagnosis module includes a plurality of sequentially connected convolution blocks, and the characteristic data output from the last convolution block is input to the failure severity module. 4. The method of claim 3,
Each of the plurality of convolution blocks, a motor failure diagnosis method, characterized in that it comprises a convolution layer and a pooling layer. 4. The method of claim 3,
The failure diagnosis module further comprises a fully connected layer that is connected to the last convolution block and outputs a failure mode. According to claim 1,
The severity estimation module includes:
A method for diagnosing a motor failure, comprising: a plurality of sequentially connected convolution blocks and a fully connected layer connected to the last convolution block to output a failure severity. 7. The method of claim 6,
Each of the plurality of convolution blocks, a motor failure diagnosis method, characterized in that it comprises a convolution layer and a pooling layer. According to claim 1,
Motor failure diagnosis method, characterized in that it further comprises the step of generating the learning data by pre-processing the phase current signal. 3. The method of claim 2,
The learning includes learning the failure diagnosis module using the input data and then learning the severity estimation module using the characteristic data, and applying the characteristic data extracted from the learned failure diagnosis module to the failure mode. Motor failure diagnosis method, characterized in that input to a corresponding severity estimation module to learn the severity estimation module. 3. The method of claim 2,
In the learning step, the failure diagnosis module and the severity estimation module are simultaneously learned, and the feature data extracted from the failure diagnosis module during the learning process is input to the severity estimation module corresponding to the failure mode, and the severity estimation module is executed. Motor failure diagnosis method, characterized in that learning. A motor fault diagnosis device comprising:
A learning unit that trains a neural network model using learning data obtained from a phase current signal of a motor - Here, the neural network model includes a failure diagnosis module for identifying a failure mode of the motor and a severity estimation module for estimating the failure severity for each failure mode including, wherein the feature data extracted from the fault diagnosis module is input to the severity estimation module; and
and a determination unit configured to determine a failure mode and a failure severity of the motor using the learned neural network model. 12. The method of claim 11,
The severity estimation module is provided to correspond to each failure mode,
The motor failure diagnosis apparatus, characterized in that the characteristic data is input to a severity estimation module corresponding to the failure mode identified through the failure diagnosis module. 12. The method of claim 11,
The failure diagnosis module includes a plurality of sequentially connected convolution blocks, and the characteristic data output from the last convolution block is input to the failure severity module. 14. The method of claim 13,
Each of the plurality of convolution blocks, motor failure diagnosis apparatus, characterized in that it comprises a convolution layer and a pooling layer. 14. The method of claim 13,
The failure diagnosis module further comprises a fully connected layer connected to the last convolution block and outputting a failure mode. 12. The method of claim 11,
The severity estimation module includes:
Motor failure diagnosis apparatus, characterized in that it comprises a plurality of convolution blocks sequentially connected and a fully connected layer connected to the last convolution block to output a failure severity. 17. The method of claim 16,
Each of the plurality of convolution blocks, motor failure diagnosis apparatus, characterized in that it comprises a convolution layer and a pooling layer. 12. The method of claim 11,
Motor failure diagnosis apparatus, characterized in that it further comprises a pre-processing unit for pre-processing the phase current signal to generate the learning data. 13. The method of claim 12,
The learning unit learns the failure diagnosis module by using the learning data and then learns the severity estimation module using the characteristic data, and uses the characteristic data extracted from the learned failure diagnosis module to correspond to the failure mode. Motor failure diagnosis apparatus, characterized in that input to the severity estimation module to learn the severity estimation module. 13. The method of claim 12,
In the learning step, the failure diagnosis module and the severity estimation module are simultaneously learned, and the characteristic data extracted from the failure diagnosis module during the learning process is input to the severity estimation module corresponding to the failure mode, and the severity estimation module is executed. Motor failure diagnosis device, characterized in that learning.

Images