KR20210059551A - Deep learning-based management method of unmanned store system using high performance computing resources - Google Patents
Deep learning-based management method of unmanned store system using high performance computing resources Download PDFInfo
- Publication number
- KR20210059551A KR20210059551A KR1020190147146A KR20190147146A KR20210059551A KR 20210059551 A KR20210059551 A KR 20210059551A KR 1020190147146 A KR1020190147146 A KR 1020190147146A KR 20190147146 A KR20190147146 A KR 20190147146A KR 20210059551 A KR20210059551 A KR 20210059551A
- Authority
- KR
- South Korea
- Prior art keywords
- motor
- current
- air gap
- frequency
- fault diagnosis
- Prior art date
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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/25—Arrangements for measuring currents or voltages or for indicating presence or sign thereof using digital measurement techniques
- G01R19/2506—Arrangements for conditioning or analysing measured signals, e.g. for indicating peak values ; Details concerning sampling, digitizing or waveform capturing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/25—Arrangements for measuring currents or voltages or for indicating presence or sign thereof using digital measurement techniques
- G01R19/252—Arrangements for measuring currents or voltages or for indicating presence or sign thereof using digital measurement techniques using analogue/digital converters of the type with conversion of voltage or current into frequency and measuring of this frequency
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R23/00—Arrangements for measuring frequencies; Arrangements for analysing frequency spectra
- G01R23/16—Spectrum analysis; Fourier analysis
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02K—DYNAMO-ELECTRIC MACHINES
- H02K17/00—Asynchronous induction motors; Asynchronous induction generators
- H02K17/02—Asynchronous induction motors
Abstract
Description
본 발명은 모터의 운전을 온라인으로 실시간으로 감시하여 고장징후를 포착하고 고장원인을 파악하여 예방정비를 할 수 있도록 취득된 전압, 전류신호를 신호처리하여 전류스펙트럼 및 토크 스펙트럼을 생성하고 모터의 운전효율을 산출하여 모터의 기계적 및 전기적 결함을 원격 자동 진단하는 모터의 고장 진단방법 및 그 시스템을 제공하는 데 있다. 더 나아가 고전압 유도전동기의 경우 낮은 슬립을 가지는 경우가 많은 데, 이는 기본주파수 성분 근처에 고장신호가 나타다나보니 진단 오류가 발생하는 경우가 종종 있다. 이를 인공지능 기술을 활용하여 오차를 낮추는 방안들이 지속적으로 연구되고 있다.The present invention generates a current spectrum and a torque spectrum by signal processing the acquired voltage and current signals so that the operation of a motor can be monitored online in real time to detect failure symptoms, identify the cause of the failure and perform preventive maintenance, and operate the motor. It is to provide a method and system for diagnosing a motor failure by calculating efficiency and remotely and automatically diagnosing mechanical and electrical defects of the motor. Furthermore, in the case of a high voltage induction motor, there are many cases with low slip, which often causes a diagnostic error because a fault signal appears near the fundamental frequency component. Methods for reducing errors by using artificial intelligence technology are continuously being studied.
근래에는 센서 없이 전압, 전류, 자속특성의 분석을 통해 모터의 고장을 조기에 진단하는 전기신호 분석방법이 이용되고 있다. 전기신호분석방법은 모터제어부(MCC: Motor Control Center)의 전압 트랜스포머(Potential Transformer)와 전류트랜스포머(CT: Current Transformer)로부터 운전중인 모터속도를 산출한 다음 유도전동기의 슬립을 계산하여 로터 바 주파수, 베어링 주파수 등을 근거로 한다.In recent years, an electric signal analysis method that diagnoses motor failure early through analysis of voltage, current, and magnetic flux characteristics without a sensor has been used. The electric signal analysis method is to calculate the running motor speed from the voltage transformer (potential transformer) and the current transformer (CT: current transformer) of the motor control unit (MCC), and then calculate the slip of the induction motor to calculate the rotor bar frequency, It is based on bearing frequency, etc.
본 발명의 목적은 온라인에 기반으로 전압,전류에 대한 신호를 효과적으로 수집하고 이 취합된 신호를 서버에서 처리를 하여 전류스펙트럼과 에어 갭 토크 스펙트럼을 생성하고 모터의 운전효율을 산출하여 모터의 기계적 및 전기적 결함을 원격 자동 진단하는 모터의 고장 진단방법 및 그 시스템을 제공하는 데 있다.It is an object of the present invention to effectively collect signals for voltage and current based on online, and process the collected signals in a server to generate a current spectrum and an air gap torque spectrum, and calculate the driving efficiency of the motor to achieve the mechanical and electrical properties of the motor. It is to provide a method and a system for diagnosing a motor failure that automatically diagnoses electrical defects remotely.
본 발명에 따른 모터의 고장진단방법은 로터바의 파손을 검출하는 로터바의 고장진단루틴, 모터의 성능을 확인시키는 진동검출루틴, 에어 갭의 동적 편심과 유사하게 에어 갭의 자속 밀도에 불균일을 주어 에어 갭 전류 및 토크의 변화로 베어링 결함을 검출하는 베어링 고장진단루틴과 모터에 대한 전체입력전력(Pin)과 순전력출력의 비를 산출하여 모터 작동효율을 근거로 모터의 고장을 진단하는 모터효율 산출루틴들로 이루어 진다.The fault diagnosis method of a motor according to the present invention detects non-uniformity in the magnetic flux density of the air gap similar to the fault diagnosis routine of the rotor bar that detects the damage of the rotor bar, the vibration detection routine that checks the performance of the motor, and the dynamic eccentricity of the air gap. A bearing failure diagnosis routine that detects bearing defects due to changes in the given air gap current and torque, and a motor that diagnoses motor failures based on motor operation efficiency by calculating the ratio of the total input power (Pin) and net power output to the motor. It consists of efficiency calculation routines.
본 발명은 모터의 주요고장의 원인으로 되는 로터바 고장, 고정자 고장 및 베어링 고장의 기계적 결함을 전압, 전류, 자속 특성분석을 통해 진단하는 전류신호분석방법으로 전원상태를 진단하는 외에 토크 분석 및 모터의 운전효율을 산출하여 진단의 신뢰성 및 정확도를 높이기고 현장에서 열적인 방법으로 고장판정이 이루어지도록 하고 있다.The present invention is a current signal analysis method that diagnoses mechanical defects of rotor bar failure, stator failure, and bearing failure that are the causes of major motor failures through voltage, current, and magnetic flux characteristic analysis. In addition to diagnosing the power state, torque analysis and motor The reliability and accuracy of diagnosis are improved by calculating the operating efficiency of the system, and failure determination is made in the field using a thermal method.
본 발명의 도면을 설명하면 다음과 같다.
도 1은 본 발명에 따른 모터의 고장진단 시스템을 상세히 보인 블록선도이고,
도 2는 본 발명에 따라 모터의 고장진단 시스템의 작동을 보인 것으로, 로터바의 고장진단루틴과 진동진단루틴을 보인 플로우챠트이며,
도 3은 본 발명에 따라 모터의 고장진단 시스템의 작동을 보인 것으로, 베어링의 결함을 감시하는 베어링고장 진단 루틴을 보인 플로우챠트이다.The drawings of the present invention will be described as follows.
1 is a block diagram showing in detail a fault diagnosis system for a motor according to the present invention,
Figure 2 is a flow chart showing the operation of the fault diagnosis system of the motor according to the present invention, the fault diagnosis routine and the vibration diagnosis routine of the rotor bar.
3 is a flow chart showing the operation of the motor fault diagnosis system according to the present invention, and showing a bearing fault diagnosis routine for monitoring bearing defects.
본 발명을 첨부도면을 참조하여 상세히 기술하면 다음과 같다.The present invention will be described in detail with reference to the accompanying drawings as follows.
본 발명의 원리에 따라 운전중인 모터의 기계적 전기적인 고장을 온라인으로 진단하기 위한 준비를 한다. 먼저, 작동중의 모터 운전 속도를 산출한다.In accordance with the principles of the present invention, preparations are made for on-line diagnosis of mechanical and electrical failures of a motor in operation. First, calculate the running speed of the motor during operation.
운전속도를 산출하는 방법으로 편심 주파수 피크를 이용하거나 로터바 통과주파수를 이용하는 것으로, 편심 주파수 피크를 이용하는 방법은 회전자의 위치에 따른 공극의 크기 변화에 의한 진폭이 결정되는 변조파가 측대역 형태의 전류 파형으로 나타나는데, 이와 같은 전류신호의 주파수의 정확한 위치는 모터의 극수와 속도의함수이다As a method of calculating the driving speed, an eccentric frequency peak is used or a rotor bar pass frequency is used.The method of using the eccentric frequency peak is a modulated wave whose amplitude is determined by a change in the size of the air gap according to the position of the rotor, in the form of a sideband. It appears as a current waveform of, and the exact position of the frequency of such a current signal is a function of the number of poles and speed of the motor.
1: 모터
20: 모터고장진단시스템
21: 전류감지부
22: 온도감지부
23: 자극위치감지부
50: 서버
60: 개인단말기
24: A/D 변환부
25: 전류피크산출부
26: 작동 검출부
27: 진동검출부
31: 모터속도 산출부
32: 속도주파수 분석부
33: 데이터분석부
34: 고장분석부
35:회전자 진단부
36: 모터상태진단부
40: 에어갭토크산출부
41: 베어링주파수산출부
42: 토크주파수분석부
43: 베어링진단부
44: 모터운전효율 산출부 45: 시간영역 분석부
46: 부하운전상태진단부1: Motor 20: Motor fault diagnosis system
21: current sensing unit 22: temperature sensing unit
23: magnetic pole position detection unit 50: server
60: personal terminal 24: A/D conversion unit
25: current peak calculation unit 26: operation detection unit
27: vibration detection unit 31: motor speed calculation unit
32: speed frequency analysis unit 33: data analysis unit 34: failure analysis unit
35: rotor diagnosis unit 36: motor condition diagnosis unit
40: air gap torque calculation unit 41: bearing frequency calculation unit
42: torque frequency analysis unit 43: bearing diagnosis unit
44: motor operation efficiency calculation unit 45: time domain analysis unit
46: load operation status diagnosis unit
Claims (2)
모터의 운전중에 발생하는 전류, 전압을 A/D변환하여 주파수 분석을 한 후 고장주파수를 검출하는 로터바의 고장진단루틴,
모터의 물리적 고장 위치를 찾아내는 알고리즘루틴,
에어 갭의 동적 편심과 유사하게 에어 갭의 자속 밀도에 불균일을 주어 에어 갭 전류 및 토크의 변화로 베어링 결함을 검출하는 베어링 고장진단루틴과
모터에 대한 전체입력전력(Pin)과 순전력출력의 비를 산출하여 모터 작동효율을 근거로 모터의 고장을 진단하는 모터효율 산출루틴들로 이루어진 것을 특징으로 하는 모터의 고장진단방법.
In the fault diagnosis method of a high voltage induction motor,
Rotor bar fault diagnosis routine that detects fault frequency after performing frequency analysis by A/D conversion of current and voltage generated during motor operation,
Algorithm routine to find the location of the physical failure of the motor,
Similar to the dynamic eccentricity of the air gap, the bearing fault diagnosis routine detects bearing defects due to changes in air gap current and torque by giving non-uniformity to the magnetic flux density of the air gap.
A method for diagnosing a failure of a motor, comprising motor efficiency calculation routines for diagnosing a failure of the motor based on the motor operation efficiency by calculating a ratio of the total input power (Pin) and the net power output to the motor.
로터바의 고장진단루틴은;
전류피크산출부가 A/D변환부로부터 전류/전압신호를 수신하고, 로터바 주파수를 산출하고, 전류피크산출부가 전류주파수에 따른 스펙트럼에서 전류피크치를 산출하여 산출된 전류 피크 치 신호를 작동검출부에 인가하여 전류 피크 치가 -45dB 이상인지 판단하고 이하이면 로터바 상태가 양호한 것으로 판단한 후 이를 점검하도록 인공지능 알고리즘루틴으로 이전하게 한 것을 특징으로하는 모터의 고장진단방법.
The method according to claim 1,
Rotor bar fault diagnosis routine;
The current peak calculation unit receives the current/voltage signal from the A/D conversion unit, calculates the rotor bar frequency, and the current peak calculation unit calculates the current peak value in the spectrum according to the current frequency, and sends the calculated current peak value signal to the operation detection unit. A fault diagnosis method of a motor, characterized in that it is applied to determine whether the current peak value is -45dB or more, and if it is less than or equal to, the rotor bar is determined to be in good condition and then transferred to an artificial intelligence algorithm routine to check it.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020190147146A KR20210059551A (en) | 2019-11-15 | 2019-11-15 | Deep learning-based management method of unmanned store system using high performance computing resources |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020190147146A KR20210059551A (en) | 2019-11-15 | 2019-11-15 | Deep learning-based management method of unmanned store system using high performance computing resources |
Publications (1)
Publication Number | Publication Date |
---|---|
KR20210059551A true KR20210059551A (en) | 2021-05-25 |
Family
ID=76145790
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020190147146A KR20210059551A (en) | 2019-11-15 | 2019-11-15 | Deep learning-based management method of unmanned store system using high performance computing resources |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR20210059551A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114355186A (en) * | 2021-11-26 | 2022-04-15 | 合肥工业大学 | Method for diagnosing rotor broken bar and speed sensor fault of asynchronous motor system |
WO2022235126A1 (en) | 2021-05-07 | 2022-11-10 | 주식회사 엘지에너지솔루션 | Porous substrate for separator, and separator for electrochemical device comprising same |
KR102572908B1 (en) * | 2023-06-01 | 2023-08-31 | 주식회사 에이테크 | Method and Apparatus for Diagnosing Dynamic Eccentricity of Electric Vehicle Traction Motor |
-
2019
- 2019-11-15 KR KR1020190147146A patent/KR20210059551A/en unknown
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022235126A1 (en) | 2021-05-07 | 2022-11-10 | 주식회사 엘지에너지솔루션 | Porous substrate for separator, and separator for electrochemical device comprising same |
CN114355186A (en) * | 2021-11-26 | 2022-04-15 | 合肥工业大学 | Method for diagnosing rotor broken bar and speed sensor fault of asynchronous motor system |
CN114355186B (en) * | 2021-11-26 | 2023-03-07 | 合肥工业大学 | Method for diagnosing rotor broken bar and speed sensor fault of asynchronous motor system |
KR102572908B1 (en) * | 2023-06-01 | 2023-08-31 | 주식회사 에이테크 | Method and Apparatus for Diagnosing Dynamic Eccentricity of Electric Vehicle Traction Motor |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101432786B1 (en) | Fault diagnosis method of motor and system thereof | |
Filippetti et al. | Condition monitoring and diagnosis of rotor faults in induction machines: State of art and future perspectives | |
KR20210059551A (en) | Deep learning-based management method of unmanned store system using high performance computing resources | |
KR20190072165A (en) | Fault diagnosis system of motor | |
CN103926506A (en) | Turbine generator rotor winding short circuit fault diagnosis method based on structured function | |
KR20200081591A (en) | Fault determining methods for the electronic motor using the wavelet transform | |
Dias et al. | A neuro-fuzzy approach for locating broken rotor bars in induction motors at very low slip | |
Djagarov et al. | Overview of diagnostic methods for rotating electrical machines | |
Shehata et al. | Detection of induction motors rotor/stator faults using electrical signatures analysis | |
Göktas et al. | A new method to separate broken rotor failures and low frequency load oscillations in three-phase induction motor | |
Irfan et al. | An intelligent fault diagnosis of induction motors in an arbitrary noisy environment | |
Deeb et al. | Three-phase induction motor short circuits fault diagnosis using MCSA and NSC | |
Fernandez-Temprano et al. | Broken bar condition monitoring of an induction motor under different supplies using a linear discriminant analysis | |
Shaeboub et al. | Detection and diagnosis of compound faults in induction motors using electric signals from variable speed drives | |
Irhoumah et al. | Diagnosis of induction machines using external magnetic field and correlation coefficient | |
KR102212084B1 (en) | Fault diagnosis method of synchronous motor | |
Pietrzak et al. | Stator phase current STFT analysis for the PMSM stator winding fault diagnosis | |
Stojičić et al. | Monitoring of rotor bar faults in induction generators with full-size inverter | |
Chouidira et al. | Continuous Wavelet Technique for Detection of Broken Bar Faults in Induction Machine. | |
Mathew et al. | Various Indices for Diagnosis of Air-gap Eccentricity Fault in Induction Motor-A Review | |
Sheikh et al. | Non-invasive methods for condition monitoring and electrical fault diagnosis of induction motors | |
Liang et al. | Fault diagnosis for induction motors using finite element method-A review | |
Parlos et al. | Sensorless detection of mechanical faults in electromechanical systems | |
Kumar et al. | A new burg method based approach to mcsa for broken rotor bar detection | |
Puche-Panadero et al. | Detection of broken rotor bar fault in induction machine fed by frequency converter |