Robust extraction of motor fault frequency components under varying operating conditions

Abstract

A fault detection system for extracting fault signatures of a motor operating under varying speed or varying load conditions is provided. The fault detection system includes a sensor interface configured to acquire sensor signals from sensors disposed at predetermined locations on the induction machine, and a memory connected to a processor, the sensor signals indicating a rotor eccentricity level of the induction machine. The instructions include steps, the sensor interface configured to acquire operating signals of the induction machine, and the memory configured to store a computer-implemented fault detection method for extracting fault signals in the frequency domain from a frequency spectrum formed by minimum variance beamforming.

Description

[Technical Field]

[0001] The present invention relates to a system for extracting fault signatures of a motor operating under varying speed or varying load conditions based on motor current signature analysis. [Background technology]

[0002] Motor current signature analysis (MCSA) has been a widely used method in the past few decades to detect motor faults such as bearing faults, eccentricity, and open circuit faults. When any of these motor faults occur, the rotating magnetic flux in the air gap becomes asymmetric, which induces extra frequency components in the stator current. MCSA-based fault detection methods aim to extract fault signatures in the frequency domain by analyzing the stator current.

[0003] In practice, extracting fault frequency components is very difficult for the following reasons. First, motor fault frequency components are generally much weaker than operating frequency components, especially in the early stages of motor fault occurrence. Second, weak fault signatures are easily buried in background noise or interference. For example, if a motor is driven by an inverter, its fault signature may be interfered with by the harmonics of the power electronics caused by the switching operation of the power electronics. Third, motors generally operate under variable load and variable speed conditions. Non-periodic time-varying factors inevitably result in spectral distortion of MCSA. Therefore, to effectively extract fault signatures from noisy measurements, it is desirable to develop a robust fault signature extraction method for motors under variable operating conditions.

[0004] Frequency spectrum analysis is a typical signal processing problem and is widely used in all kinds of applications. The most common spectrum analysis method for MCSA-based fault detection is the Fourier transform, due to its ease of use. This method works well when the test motor is operating at a steady state, but not so well when the load is changing. In the latter case, a simple method is to measure multiple time sequences and take their average, which can average out the effects of noise and changing operation. However, this method requires longer measurement times and may not be effective in extracting small fault signatures. To achieve high-resolution spectra, researchers have introduced other advanced signal processing methods, such as ESPRIT, MUSIC, and compressed sensing (CS), to motor fault detection. However, these methods are sensitive to noise or heavily rely on signal models. Low noise levels or small load changes occurring during the measurement period can hinder the accuracy of fault detection.

[0005] Therefore, there is a need for a robust method for extracting fault signatures of motors operating under varying speed or varying load conditions. Summary of the Invention

[0006] Motor current spectrum analysis (MCSA) is widely used for motor fault detection, including bearing faults, eccentricity, and open wires. When a motor fault is in its early stages or when a faulty motor is operating under varying load conditions, the fault signature may be buried in background noise and interference, making fault detection extremely difficult. Some embodiments of the present invention provide a method and system for extracting fault signatures with small frequency components under conditions of varying load and strong background noise. To this end, we divide time-domain current measurements into overlapping sequences and treat these sequences as measurements from a linear sensor array. We then employ minimum variance beamforming for array signal processing to generate a current spectrum with robust performance under varying load operation. We demonstrate our method using experimental data collected on a motor operating under realistic varying conditions and with a small eccentricity fault.

[0007] Some embodiments of the present invention provide a minimum variance-based spectral analysis method (minimum variance beamforming) for extracting frequency components of motor faults in the early stages as operating conditions change. Minimum variance beamforming minimizes the noise variance of the spectrum at each frequency. Therefore, in the final frequency spectrum, noise-related frequency components are suppressed while the frequency components of the signal, including the fault signal, are preserved. Experimental results demonstrate the effectiveness of the present method for extracting fault signatures from noisy measurements.

[0008] An objective of some embodiments is to provide a system and method suitable for extracting fault signatures from motors operating under varying speed or load conditions. Motivated by array signal processing methodology, the inventors propose performing motor current spectrum analysis using minimum variance beamforming. The detailed concept is as follows: First, the inventors divide the time-domain stator current under test into multiple overlapping time sequences with a fixed time shift. Each sequence is treated as an independent measurement of a virtual current sensor. Because the time difference between adjacent sequences is identical, these virtual sensors form a linear virtual sensor array. Next, the spectral analysis problem is transformed into a linear array beamforming problem in the frequency domain. The inventors borrow the idea of ​​minimum variance (MV) beamforming from array signal processing technology to improve detection performance under noisy measurement conditions. Due to variations in motor operating conditions, each sensor has a gain coefficient that depends on a different unknown frequency. MV-based spectral analysis aims to achieve a robust spectrum by using a weighted sum of the spectra of each time sequence. The weights are frequency dependent and are optimized by minimizing the noise variance of the output spectrum.

[0009] To verify the proposed method of the present invention, we used motor eccentricity as an example to perform fault detection based on MCSA. Specifically, in this experiment, a motor with a minor eccentricity fault was used as the experimental subject, and a magnetic powder brake was attached as the motor load. The input current of the magnetic powder brake was then changed to measure the motor's stator current under variable load conditions. By comparing the MCSA results of experimental data obtained using different methods, we demonstrated that the method of the present invention can effectively extract fault frequency components under variable load conditions, even under strong noise interference.

[0010] According to some embodiments of the present invention, a fault detection system for extracting a fault signature of an induction machine operating under varying load or varying speed conditions is provided. The fault detection system may include a sensor interface configured to acquire an operating signal of the induction machine, a memory configured to store a computer-implemented fault detection method, and a digital signal processor configured to execute steps of the computer-implemented fault detection method using the operating signal acquired via the sensor interface. The steps of the computer-implemented fault detection method include dividing the operating signal into N segments based on a time window, the division being performed on each of the N segments to include an overlap period between adjacent divided operating signals, transforming each of the divided operating signals into N frequency domains, shifting the phase of each of the divided operating signals by a predetermined phase, and performing beamforming on the transformed divided operating signals, applying optimized weighting coefficients to each of the transformed divided operating signals, and extracting a fault signal in the frequency domain from a frequency spectrum formed by the minimum variance beamforming method.

[0011] Some embodiments of the present invention further provide a computer-implemented fault detection method for extracting a fault signature of an induction machine operating under varying load or varying speed conditions, including: acquiring an operating signal of the induction machine through a sensor interface connected to a current sensor disposed in the induction machine; dividing the operating signal into N segments based on a time window, the division being performed on each of the N segments to include an overlapping period between adjacent divided operating signals; transforming each of the divided operating signals into N frequency domains; shifting the phase of each of the divided operating signals by a frequency and a sequence time-shift-related phase; and performing minimum variance beamforming on the transformed divided operating signals, applying optimized weighting coefficients to each of the transformed divided operating signals, and extracting a fault signal in the frequency domain from the frequency spectrum formed by the minimum variance beamforming.

[0012] The accompanying drawings, which are included to provide a further understanding of the invention, illustrate embodiments of the invention and, together with the description, explain the principles of the invention. The drawings illustrated are not necessarily to scale. Instead, emphasis may be placed upon illustrating the principles of embodiments of the present disclosure. [Brief explanation of the drawings]

[0013] [Figure 1A] 1 is a schematic diagram illustrating a fault detection system for controlling and monitoring an induction motor in accordance with one embodiment of the present invention; [Figure 1B] 1 is a schematic diagram illustrating a fault detection system operated by a user (operator) over a network to control and monitor an induction motor in accordance with one embodiment of the present invention. [Figure 2A] FIG. 1 illustrates a normal motor with a uniform air gap, in accordance with one embodiment of the present invention. [Figure 2B] FIG. 1 illustrates an eccentric motor with a non-uniform air gap, in accordance with one embodiment of the present invention. [Figure 3]1 is an exemplary plot showing stator current in the time domain. [Figure 4] FIG. 1 is a block diagram illustrating an MCSA-based fault detection system for detecting rotor faults in accordance with one embodiment of the present invention. [Figure 5] FIG. 2 is a block diagram illustrating details of a robust spectral analysis method in accordance with one embodiment of the present invention. [Figure 6A] 1 is an exemplary plot showing stator current spectra under one load condition using Fourier transform spectra. [Figure 6B] 1 is an exemplary plot showing stator current spectra under one load condition using an average spectrum. [Figure 6C] 1 is an exemplary plot showing stator current spectra under one load condition using minimum variance (MV) spectra. [Figure 7A] 10 is an exemplary plot illustrating stator current spectra under different load conditions using Fourier transform spectra; [Figure 7B] 10 is an exemplary plot showing stator current spectra under different load conditions using an average spectrum; [Figure 7C] 10 is an exemplary plot showing stator current spectra under different load conditions using minimum variance (MV) spectra. [Figure 8A] 10 is an exemplary plot illustrating stator current spectra under different load conditions using Fourier transform spectra; [Figure 8B] 10 is an exemplary plot showing stator current spectra under different load conditions using an average spectrum; [Figure 8C] 10 is an exemplary plot showing stator current spectra under different load conditions using minimum variance (MV) spectra. DETAILED DESCRIPTION OF THE INVENTION

[0014] Various embodiments of the present invention will now be described with reference to the drawings. Note that the drawings are not drawn to scale, and elements having similar structure or function are designated by similar reference numerals throughout the drawings. Furthermore, the drawings are intended to facilitate the description of specific embodiments of the present invention. The drawings are not intended as an exhaustive description of the invention or as limitations on the scope of the invention. Furthermore, features described in connection with a particular embodiment of the present invention are not necessarily limited to that embodiment and may be implemented in any other embodiment of the present invention.

[0015] FIG. 1A is a schematic diagram illustrating a fault detection system 100 for controlling and monitoring an induction motor, in accordance with one embodiment of the present invention.

[0016] Induction motor (system) 200 includes a rotor assembly 102, a stator assembly 104, a main shaft 106, and two main bearings 108. In this example, induction motor 200 is a squirrel-cage induction motor.

[0017] Controller 220 is powered by power supply 230 and can be used to monitor and control the operation of induction motor 200 in response to various inputs in accordance with embodiments of the present invention. For example, controller 220 connected to induction motor 200 can control the speed of the induction motor based on inputs received from fault detection system 100, which is configured to obtain data regarding the operating conditions of induction motor 200 from current sensor 150 and obtain stator current data to induction motor 200. For example, the current sensor senses current data from one or more of the induction motor's phases. More specifically, if the induction motor is a three-phase induction motor, the current sensor senses current data from all three phases of the three-phase induction motor. While certain embodiments of the present invention are described with respect to a polyphase induction motor, other embodiments of the present invention may be applied to other polyphase electric machines.

[0018] Some embodiments of the present invention describe a system for detecting faults in an electric machine, such as an induction motor 200. The configured detection system includes a fault detection circuit module 100 for detecting faults in a rotor 102, including eccentricity faults, open circuit faults, and eccentricity faults, within an induction motor assembly. In one embodiment, the fault detection circuit module 100 is implemented as a subsystem of a controller 220. In some cases, the fault detection circuit module 100 may be referred to as a fault detection system. In an alternative embodiment, the fault detection circuit module 100 is implemented using a separate processor. The fault detection circuit module 100 may be a hardware circuit module operably connected to the controller 220. In some implementations, the fault detection circuit module 100 and the controller 220 can share information. For example, the fault detection circuit module 100 can reuse sensor data used by the controller to control the operation of the induction motor.

[0019] Fault detection circuit module 100 also includes processor 110, memory 120, and a fault detection program (computer-implemented fault detection method) stored in memory 120, where instructions of the fault detection program are executed by processor 110. Circuit module 100 further includes a sensor interface 130 configured to acquire a signal from sensor 150. Sensor interface 130 includes an A / D (analog-to-digital) and an A / D (analog-to-digital) converter for data communication with processor 110, memory 120, the fault detection program, user interface 140, and current sensor 150. Processor 110 is a digital signal processor configured to acquire a digital signal of the stator current (motor current) of the induction motor from current sensor 150 via sensor interface 130 and to execute steps of the fault detection program.

[0020] The processor 110 may be multiple processors, and the memory 120 may be a memory module including multiple memories. The user interface 140 is configured to connect to a keyboard and display unit configured to display normal / fault status information of the induction motor 200 in response to the output of the fault detection module 200.

[0021] FIG. 1B is a schematic diagram illustrating a fault detection system operated by a user (operator) via a network 250 to control and monitor an induction motor according to one embodiment of the present invention. In this case, fault detection module 100 may be included in the operating system of the induction motor located at the user / operator's site. If fault detection module 100 determines that a fault has occurred based on a sensor signal from sensor 150 obtained via network (communication network) 250 during operation of induction machine (induction motor) 200, fault detection module 100 can slow down or stop the operation of induction motor 200 by transmitting a control signal via network 250 based on a pre-programmed algorithm (not shown) stored in memory 120. In some cases, current sensor 150 may be calibrated based on a sensor calibration program (not shown) stored in the memory of fault detection module 100. In some cases, network 250 may be an optical fiber network, a wireless network, an Internet network, or a data communication network consisting of a combination of at least two of an optical fiber network, a wireless network, and an Internet network.

[0022] This configuration may be a maintenance system managed by a user / client that operates induction machine system 20 located separately from the induction machine location. For example, this system configuration may be used in a power generation system operated by a user and a train system that controls an induction motor that drives a train. In some cases, when fault detection module 100 detects that the induction machine location and the fault detection system location are separated, data communication is performed between the induction machine location and the fault detection system location via a network. Network 250 may be a data communication network consisting of an optical fiber network, a wireless network, an Internet network, or a combination of at least two of an optical fiber network, a wireless network, and an Internet network.

[0023] Furthermore, a fault detection system is included as part of the user's maintenance system, and if the determined eccentricity level of the induction machine is equal to or greater than a critical threshold level, the fault detection system sends a control signal via the network to the induction machine controller using the sensor interface / control interface 130 to shut down the induction machine.

[0024] In one embodiment of the present invention, the current and voltage sensors respectively detect stator current data from the stator assembly 104 of the induction motor 200. The current data obtained from the current sensors is transmitted to the inverter for control and to the fault detection module for further processing and analysis. The analysis includes detecting a fault in the induction motor 200 by performing a motor current signature analysis (MCSA). In some embodiments, upon detecting a fault using the fault detection module 100, the controller 220 receives a fault detection signal via the interface 130 of the fault detection module 100 and stops operation of the induction motor by transmitting an interrupt signal to the controller 110 that interrupts the stator current of the induction motor 200 for further inspection or repair. In some cases, the current sensor 150 includes a controller interface (not shown) configured to receive the fault detection signal from the interface 130 and transmit a fault condition signal to the controller 220, thereby enabling the controller 220 to stop operation of the induction motor 200 by interrupting the stator current of the induction motor 200. When current sensor 150 does not include a controller interface, interface 130 may be configured to connect to controller 220 so that the controller responds to a fault detection signal from fault detection circuit module 100 via interface 130 and stops operation of induction motor 200 by interrupting the stator current of induction motor 200.

[0025] The system also includes a memory for storing signal measurements and various parameters and coefficients for implementing the fault severity detection method.

[0026] 2A and 2B are diagrams illustrating a normal motor with a uniform air gap and a faulty motor with an eccentricity fault indicated by an uneven air gap, respectively, in accordance with one embodiment of the present invention. Based on the physical model of the induction machine and the fault detection method using different features of the induction machine of the present invention, the present invention aims to extract the fault signature of a motor operating under varying speed or varying load conditions.

[0027] Motor current signature analysis (MCSA) has been widely used for motor fault detection for decades due to its effectiveness and non-invasive characteristics. The MCSA method aims to extract the characteristic frequency components of different types of faults based on the stator current frequency spectrum.

[0028] For example, if a squirrel-cage induction motor experiences an open-circuit fault, a set of new frequency components will appear in the stator current spectrum in addition to the operating frequency components.

number

[0029]

number

number

number

number

number

number

number

[0030]

number

[0031] Therefore, for most motor fault detection problems, the goal of MCSA-based methods is to extract the corresponding fault signature components through effective frequency spectrum analysis. When a fault frequency component exceeding a certain threshold is detected, it is determined that a corresponding fault exists. Depending on the amplitude of the fault frequency component and other operating conditions, the severity level of the fault can be further estimated.

[0032]

number

[0033]

number

[0034]

number

[0035]

number

[0036]

number

[0037] Figure 4 is a block diagram illustrating a computer-implemented fault signature / signal detection method / program 121 for detecting rotor faults based on MCSA, and Figure 5 is a block diagram illustrating details of a robust spectrum analysis method according to some embodiments of the present invention. The computer-implemented fault signature / signal detection method 121 is stored in memory 120 or a storage device (not shown) and is configured to be executed by processor 110 when the system performs fault detection on induction machine 200.

[0038]

number

[0039]

number

[0040]

number

[0041]

number

[0042]

number

[0043]

number

number

[0044] w is frequency-dependent. That is, for each frequency, a different w is obtained by solving Equation (25). Once the estimated spectrum S(w) 425 is obtained, at 430, fault signatures are extracted at different frequencies according to (1) through (8). At 440, if the amplitude of the fault signature is greater than a specific value, e.g., −70 dB, compared with the operating signal of an early-stage fault, the computer-implemented fault detection method / program generates a fault signature code indicating that a fault (fault signature) has been detected. In this case, the fault signature code indicates one of the severity levels of the fault based on the amplitude of the fault signature. For example, the severity level is determined by three levels corresponding to a normal level (<−70 dB), a warning level (≈−60 dB), and a severe (critical) level (>−40 dB). A corresponding control signal 450 is then sent to the controller 220 to control the induction machine 200. If no fault is detected, fault detection system 100 is configured to continue receiving / acquiring the operating current (stator current 410) of induction machine 200 from current sensor 150 via sensor interface 130 and continue monitoring stator current 410. While acquiring operating current 410 from current sensor 150 via sensor interface 130, fault detection system (circuit module) 100 continues to generate severity-level status data of the induction machine and send it to user interface 140, causing the display unit to display severity-level message information (status information). In some cases, a keyboard connected to user interface 140 is used to send a control signal to controller 220 via network 250 to control the rotational speed of induction machine 220 in response to the displayed severity-level status information of induction machine 220.

[0045] Also, if the severity level of the induction machine is equal to or greater than the critical threshold level, the fault detection system sends a control signal to the controller 220 of the induction machine 200 via the network 250 to reduce the rotational speed of the induction machine 200 or stop the operation of the induction machine 200.

[0046] To verify the proposed method, an eccentricity fault is considered as an example of an MCSA-based analysis. Experiments are conducted in the laboratory using a motor with an eccentricity fault. To generate rotor eccentricity, the two bearings supporting the rotor are removed and replaced with two external bearings fixed outside the motor. This allows for manual adjustment of the air gap to a predetermined range. Four gap sensors are placed on the stator to monitor the horizontal and vertical air gaps at both ends and ensure adjustment accuracy. A magnetic powder brake, whose torque can be adjusted by changing the input current, is used as the load. The experimental setup is shown in Figure 1A. During operation, the three-phase time-domain stator current is recorded for further analysis.

[0047]

number

[0048]

number

[0049]

number

[0050] It can be seen that the FM spectrum cannot detect fault signatures under conditions of varying loads. The averaged spectrum reduces noise to some extent and sometimes works well, but it is inconsistent. On the other hand, the MV spectrum achieved by the proposed method consistently and successfully detects fault signature components (in this case, eccentricity components with frequencies of 30 Hz and 90 Hz) for different fluctuating loads. In other words, the frequency range of the MV spectrum is set to show the fault signatures at the eccentricity components with frequencies of 30 Hz and 90 Hz.

[0051] The embodiments of the present disclosure described above may be implemented in many ways. For example, the embodiments may be implemented in hardware, software, or a combination thereof. If implemented in software, the software code may be executed on any suitable processor or group of processors, whether located on a single computer or distributed across multiple computers. Such a processor may be implemented as an integrated circuit. A single integrated circuit element may include one or more processors. However, the processor may be implemented in any suitable circuit.

[0052] The embodiments of the present disclosure may be embodied as methods, which are provided by way of example. The operations performed as part of the method may be ordered in any suitable manner. Thus, embodiments may be constructed that perform operations in an order different from the operations performed sequentially in the exemplary embodiments, and that may include performing some operations simultaneously.

[0053] The use of ordinal terms, e.g., first, second, etc., to modify claim elements in a claim does not imply a priority, precedence, or order of one claim element relative to another, or a chronological order in which the actions of a method are performed, but is merely used as a label to distinguish the claim elements and to distinguish one claim element having a particular name (by the use of ordinal terms) from another element having the same name.

[0054] Although the invention has been described with reference to preferred embodiments, it should be understood that various other modifications and variations can be made within the spirit and scope of the invention.

[0055] Accordingly, the appended claims are intended to cover all such changes and modifications as fall within the true spirit and scope of this invention.

Claims

1. 1. A fault detection system for extracting fault signatures of an induction machine operating under varying load or varying speed conditions, comprising: a sensor interface configured to acquire an operation signal of the induction machine; a memory configured to store a computer-implemented fault detection method; a digital signal processor configured to perform the steps of the computer-implemented fault detection method using the operating signals obtained via the sensor interface; The steps include: dividing the operating signal into N segments based on a time window, the division being performed for each of the N segments to include an overlap period between adjacent divided operating signals; transforming each of the divided operating signals into N frequency domains; Shifting the phase of each of the divided operating signals by a predetermined phase; performing beamforming on the transformed divided operating signals, wherein optimized weighting coefficients are applied to each of the transformed divided operating signals; and extracting a fault signal in the frequency domain from the frequency spectrum formed by minimum variance beamforming.

2. The fault detection system of claim 1 , wherein the sensor interface repeatedly acquires the operating signal over a predetermined period of time.

3. 2. The fault detection system of claim 1, wherein the eccentricity-related frequency range is determined at about half an operating frequency of the induction machine and about one and a half times the operating frequency.

4. The digital signal processor operates at a sampling rate of f ｓａ 2. The fault detection system of claim 1, wherein the operating signal is collected for 60 seconds at 10 kHz or at least twice the maximum frequency of the signal.

5. The fault detection system of claim 1 , wherein the operating signal is a stator current of the induction machine.

6. The fault detection system of claim 1 , wherein the extracted frequency spectrum is a minimum variance (MV) spectrum.

7. The fault detection system of claim 6 , wherein the frequency range of the MV spectrum is set to exhibit the fault signature at eccentric frequency components of 30 Hz and 90 Hz.

8. The induction machine is located away from the fault detection system, data communication between the location of the induction machine and the location of the fault detection system is performed via a network; 2. The fault detection system of claim 1, wherein the network is a data communication network consisting of an optical fiber network, a wireless network, an Internet network, or a combination of at least two of the optical fiber network, the wireless network, and the Internet network.

9. 9. The fault detection system of claim 8, wherein if the severity level of the induction machine is equal to or greater than a critical threshold level, the fault detection system reduces the rotational speed of the induction machine or stops operation of the induction machine by sending a control signal to a controller of the induction machine via the network.

10. 1. A computer-implemented fault detection method for extracting fault signatures of an induction machine operating under varying load or varying speed conditions, comprising: acquiring an operation signal of the induction machine through a sensor interface connected to a current sensor disposed in the induction machine; and dividing the operating signal into N segments based on a time window, the division being performed for each of the N segments to include an overlap period between adjacent divided operating signals; transforming each of the divided operating signals into N frequency domains; shifting the phase of each of the divided operating signals by a frequency and sequence time shift related phase; performing a minimum variance beamforming method on the converted divided operating signals, wherein optimized weighting coefficients are applied to each of the converted divided operating signals; and extracting a fault signal in the frequency domain from the frequency spectrum formed by minimum variance beamforming.

11. The computer-implemented fault detection method of claim 10 , wherein the sensor interface repeatedly acquires the operating signals over a predetermined period of time.

12. 11. The computer-implemented fault detection method of claim 10, wherein the eccentricity related frequency range is determined at about half an operating frequency of the induction machine and about one and a half of the operating frequency.

13. The method includes using a digital signal processor to generate a signal at a sampling rate of f ｓａ 11. The computer-implemented fault detection method of claim 10, wherein data for the operating signal is collected for 60 seconds at 10 kHz or at least twice the maximum frequency of the signal.

14. The computer-implemented fault detection method of claim 10 , wherein the operating signal is a stator current of the induction machine.

15. 11. The computer-implemented fault detection method of claim 10, wherein the extracted frequency spectrum is a minimum variance (MV) beamformed spectrum.

16. 16. The computer-implemented fault detection method of claim 15, wherein the frequency range of the MV spectrum is set to exhibit the fault signature at eccentric frequency components of 30 Hz and 90 Hz.

17. The induction machine is located away from the fault detection system, data communication between the location of the induction machine and the location of the fault detection system is performed via a network; 11. The computer-implemented fault detection method of claim 10, wherein the network is a data communication network consisting of an optical fiber network, a wireless network, an Internet network, or a combination of at least two of the optical fiber network, the wireless network, and the Internet network.

18. 18. The computer-implemented fault detection method of claim 17, wherein if the severity level of the induction machine is equal to or greater than a critical threshold level, the fault detection system reduces the rotational speed of the induction machine or stops operation of the induction machine by sending a control signal to a controller of the induction machine via the network.

Images