WO2024046166A1 - 一种故障检测方法以及相关装置 - Google Patents

一种故障检测方法以及相关装置 Download PDF

Info

Publication number
WO2024046166A1
WO2024046166A1 PCT/CN2023/114145 CN2023114145W WO2024046166A1 WO 2024046166 A1 WO2024046166 A1 WO 2024046166A1 CN 2023114145 W CN2023114145 W CN 2023114145W WO 2024046166 A1 WO2024046166 A1 WO 2024046166A1
Authority
WO
WIPO (PCT)
Prior art keywords
current
motor
fault
harmonic
amplitudes
Prior art date
Application number
PCT/CN2023/114145
Other languages
English (en)
French (fr)
Inventor
王萌
孟超
陈润昌
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2024046166A1 publication Critical patent/WO2024046166A1/zh

Links

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

Definitions

  • the present application relates to the field of fault detection, and in particular, to a fault detection method and related devices.
  • Motors are the most common equipment for driving various machinery in the production process. They are widely used in industrial production, transportation, infrastructure, agricultural development, and daily life. The electricity consumption of motors accounts for 10% of the total production electricity consumption. More than 80%. As an electrical equipment that provides power to many industries, it has many potential failure factors. Downtime due to failures will cause great economic losses. If motor faults can be detected in time and repairs and maintenance are carried out at the early stage of motor failure, the service life of the motor can be effectively extended and the reliability and stability of the entire production system can be improved.
  • the motor's protection settings appear to be perfect, but in actual operation, the relay will only sound an alarm when a motor failure occurs. However, if the motor suddenly loses power or stops running, it will cause huge losses. Therefore, it is necessary to identify potential faults in the motor. It should be understood that the existence of potential faults in the motor does not mean that the motor has failed, but is a deterioration phenomenon that appears before the failure occurs. In order to be able to identify potential faults in the motor, there is an urgent need for a method that can determine the degree of motor faults and identify potential faults in the motor.
  • This application provides a fault detection method that can determine the extent of potential faults in the motor.
  • a first aspect of the present application provides a fault detection method.
  • the method includes: obtaining a first current, which is the stator current of the motor; obtaining first characteristic data of the first current according to the first current, and the first characteristic data and It is related to the fault of the motor; the first characteristic data is the numerical relationship between the plurality of first harmonic amplitudes of the first current and the plurality of first amplitudes, and the plurality of first amplitudes include the first fundamental wave of the first current.
  • amplitude and multiple second harmonic amplitudes the multiple first harmonic amplitudes are related to the fault of the motor, and the multiple second harmonic amplitudes are not related to the fault of the motor; according to the first characteristic data, the fault of the motor is determined degree.
  • the fault-related harmonic components in the stator current caused by noise such as working conditions may be different. That is to say, even if the fault level of the motor is Similarly, under different motors or under different working conditions, the magnitude of harmonics related to faults may also be different.
  • the amplitude of the harmonic current related to the fault and the fundamental wave obtained by decomposing the stator current and the harmonics unrelated to the fault are used as features. It can be used to determine the degree of fault, which can eliminate the influence of different working conditions or motors on the magnitude of harmonic current and determine the accurate degree of fault.
  • the relevant operating parameters of the motor can be analyzed.
  • the stator current is a relatively sensitive state parameter inside the motor, and as a non-invasive method
  • the sensing signal is easy to obtain and can be collected directly in the distribution cabinet.
  • the fault degree of the motor can be determined by analyzing the harmonic components of the stator current. When a potential fault occurs in the motor, it will cause the unevenness of the motor's magnetic field. The above phenomenon will be directly reflected in the stator current. For example, there will be obvious harmonic components in the current or the fluctuation of the phase value will be unstable. This phenomenon
  • the application extracts characteristic data from the signal (stator current) caused by the potential fault of the motor. This characteristic data reflects the abnormal components in the stator current.
  • the degree of potential fault in the motor can be determined based on this characteristic data.
  • one or more phases of three-phase power may have partial or abnormal current values (there are obvious value jumps and other abnormal conditions).
  • the corresponding current value of one or two other phases can be used to complete (because the currents of different phases in three-phase power are only different in phase under normal circumstances, the amplitude is identical).
  • the correlation between currents can be used for signal preprocessing.
  • the amplitudes of aligned phases in multiple phases (for example, two phases or three phases) of three-phase electricity can be fused and used as the first current.
  • fusion can be the splicing of amplitudes of different phases, or averaging.
  • the numerical relationship between the plurality of first harmonic amplitudes and the plurality of first amplitudes includes: a first difference between a first fusion result and a second fusion result. degree; the first fusion result is the fusion result of the plurality of first harmonic amplitudes; the second fusion result is the fusion result of the plurality of first amplitudes.
  • the above-mentioned fusion result of multiple first harmonic amplitudes related to the potential fault of the motor can represent the energy related to the potential fault of the motor
  • the multiple amplitudes of The fusion result may represent the total energy (for example, the total energy including the energy related to the fault, or the total energy excluding the energy related to the fault)
  • the numerical relationship between the first harmonic amplitude and multiple first amplitudes that is, the numerical relationship between the energy related to potential faults of the motor and the total energy, can characterize the degree of potential faults in the motor.
  • the first current is the stator current of the motor during a first time period
  • the method further includes: obtaining a second current, where the second current is the stator current of the motor during normal operation or during the first time period.
  • the stator current in two time periods, the second time period being the time period before the first time period;
  • determining the fault degree of the motor according to the first characteristic data includes: according to the first characteristic data Two currents, obtain the second characteristic data of the second current, the second characteristic data and the first characteristic data are data calculated in the same way; according to the first characteristic data and the second characteristic The difference between the data determines the degree of failure of the motor.
  • the first time period may be a continuous time period or multiple moments within a continuous time period, and the first time period may also be a discontinuous time period or within a discontinuous time period. Multiple moments are not limited here.
  • the first current may be an instantaneous value of the current at each moment in multiple moments within a time period.
  • different motors may have different amplitudes of fundamental waves or harmonics.
  • Merely using the characteristic data of the motor in a certain period of time cannot Accurately describe the degree of potential failure of the motor.
  • the characteristic data of the motor during normal operation or historical operation time period can be used as the benchmark, and the difference between the real-time characteristic data of the motor and the benchmark can be used. Comparison is used to determine the degree of potential faults of the motor, which can then reduce the interference of different motors or the same motor in different operating environments.
  • the second characteristic data and the first characteristic data are data calculated in the same way.
  • the plurality of first harmonic amplitudes are the values in the first current. Amplitudes of a plurality of harmonics of the first frequency; the second characteristic data is a plurality of third harmonic amplitudes and a plurality of second harmonics of the plurality of harmonics of the first frequency in the second current.
  • the plurality of third harmonic amplitudes are the amplitudes of the plurality of harmonics of the first frequency in the second current, and the plurality of second amplitudes include the third The fundamental wave amplitude of the second current and a plurality of harmonic amplitudes that are not related to the fault of the motor; the second current is the stator current of the motor when no fault occurs, or the stator current in the second time period .
  • each first harmonic amplitude among the plurality of first harmonic amplitudes and each corresponding fourth harmonic amplitude among the plurality of fourth harmonic amplitudes are in Within the preset numerical range, each fourth harmonic amplitude is the amplitude of a harmonic that is a multiple of the harmonic frequency corresponding to the first harmonic amplitude; or, multiple first harmonic amplitudes are equal to the corresponding harmonic amplitude.
  • the fusion result of multiple fourth harmonic amplitudes is within the preset value range.
  • harmonic product spectrum is used to accurately extract non-noise harmonic components.
  • the principle is that noise generally only causes a single harmonic, and a fault not only causes harmonics at the fault frequency point, but also causes harmonic components at multiples of the fault frequency.
  • the potential faults of the motor can be combined Relevant harmonic characteristics are amplified and noise is removed.
  • the characteristic data includes the amplitude of the fundamental wave of the first current (for example, the amplitude of the first fundamental wave in the embodiment of the present application) and multiple The amplitude of a harmonic (for example, the multiple first harmonic amplitudes in the embodiment of the present application), wherein the multiple first harmonic amplitudes among the multiple first harmonic amplitudes are related to the potential existence of the motor.
  • the amplitude of the harmonic related to the fault, and the fusion result of each first harmonic amplitude of the plurality of first harmonic amplitudes and the corresponding plurality of fourth harmonic amplitudes (for example, the fusion result may be (obtained by product operation, neural network, etc.) meeting the preset conditions, or each first harmonic amplitude among the multiple first harmonic amplitudes and each of the corresponding fourth harmonic amplitudes.
  • the fourth harmonic amplitudes all meet the preset conditions.
  • Each fourth harmonic amplitude is the amplitude of a harmonic that is a multiple of the harmonic frequency corresponding to the first harmonic amplitude.
  • the preset condition can be that the value is greater than threshold.
  • each fourth harmonic amplitude is the amplitude of a harmonic that is a multiple of the harmonic frequency corresponding to the first harmonic amplitude.
  • the harmonic frequencies related to potential faults at different structural positions on the motor are different, and there is a corresponding relationship (the structure of the motor and the harmonic frequency).
  • Different motors have different motor structures, and the correspondence between the structure and the harmonic frequency The relationship may also be different.
  • the corresponding relationship between the structure of the motor and the harmonic frequency can be used as prior information, and it is determined which structures of the motor appear by analyzing whether the harmonic frequency is abnormal. Even if the frequency corresponding to the motor structure is abnormal and does not belong to the corresponding relationship, even if the value is greater than a certain threshold, it is considered not to be the harmonic frequency corresponding to the faulty component. This means that current technology relies on prior information when performing fault detection.
  • the degree of potential failure present may be represented by a potential failure level, such as severe, moderate, or minor.
  • the degree of potential failure present may be represented by a potential failure score, for example a value between 0 and 100.
  • the existing potential fault degree can be represented by comparative information of the potential fault degree of the electrode and the potential fault degrees of other motors, such as the ranking of the potential fault degree of the motor.
  • this application provides a fault detection method.
  • the method includes: obtaining a first current, which is the stator current of the motor; and obtaining first characteristic data of the first current according to the first current. It includes the first change characteristic in the time domain of the first phase value corresponding to the first current; the first phase value is the phase in the complex signal obtained by decomposing the first current; the first change characteristic and the first phase value in the time domain It is related to the amplitude of change; according to the first characteristic data, the degree of fault of the motor is determined.
  • the characteristic data includes the first change characteristic in the time domain of the first phase value corresponding to the first current; the phase value is the phase in the complex signal obtained by decomposing the first current.
  • the first change characteristic may be related to the change amplitude of the first phase value in the time domain.
  • the change amplitude may be represented by an average of peak-to-peak values.
  • the first current is the stator current of the motor during the first time period
  • the method further includes: obtaining a second current
  • the second current is the stator current of the motor during normal operation or during the second time period
  • the second time period is the time period before the first time period
  • determining the fault degree of the motor according to the first characteristic data includes: obtaining second characteristic data of the second current according to the second current, the second characteristic data and The first characteristic data is data calculated in the same way; based on the difference between the first characteristic data and the second characteristic data, the degree of fault of the motor is determined.
  • the second characteristic data includes a second change characteristic in the time domain of the second phase value corresponding to the second current;
  • the second phase value is the phase in the complex signal obtained by decomposing the second current;
  • the second change characteristic is related to the change amplitude of the second phase value in the time domain.
  • the existing fault level is represented by fault level, fault score, or comparison information of the fault level of the electrode with the fault level of other motors.
  • this application provides a fault detection device, which includes:
  • the acquisition module is used to acquire the first current, which is the stator current of the motor;
  • the feature extraction module is used to obtain first characteristic data of the first current according to the first current.
  • the first characteristic data is related to the fault of the motor;
  • the first characteristic data is a plurality of first harmonic amplitudes and multiple first harmonic amplitudes of the first current.
  • the fault determination module is used to determine the fault degree of the motor based on the first characteristic data.
  • the first current is the stator current of the motor in the first time period
  • the acquisition module is also used to:
  • the second current is the stator current of the motor during normal operation or during the second time period, and the second time period is the time period before the first time period;
  • Feature extraction module also used for:
  • second characteristic data of the second current is obtained, and the second characteristic data and the first characteristic data are data calculated in the same way;
  • Fault determination module specifically used for:
  • the fault degree of the motor is determined.
  • the numerical relationship between multiple first harmonic amplitudes and multiple first amplitudes includes:
  • the plurality of first harmonic amplitudes are the amplitudes of multiple harmonics of the first frequency in the first current
  • the second characteristic data is a numerical relationship between a plurality of third harmonic amplitudes of the second current and a plurality of second amplitudes; the plurality of second amplitudes include the fundamental amplitude of the second current and a plurality of harmonics. amplitude; the second current is the stator current of the motor when no fault occurs, or the stator current in the second time period; the plurality of third harmonic amplitudes are the harmonics of the plurality of first frequencies in the plurality of second amplitudes. The amplitude of the wave.
  • each first harmonic amplitude among the plurality of first harmonic amplitudes and each corresponding fourth harmonic amplitude among the plurality of fourth harmonic amplitudes are in Within the preset numerical range, each fourth harmonic amplitude is the amplitude of a harmonic that is a multiple of the harmonic frequency corresponding to the first harmonic amplitude; or,
  • the fusion result of the plurality of first harmonic amplitudes and the corresponding plurality of fourth harmonic amplitudes is within a preset numerical range.
  • the existing fault level is represented by fault level, fault score, or comparison information of the fault level of the electrode with the fault level of other motors.
  • this application provides a fault detection device, which includes:
  • the acquisition module is used to acquire the first current, which is the stator current of the motor;
  • the feature extraction module is used to obtain the first characteristic data of the first current according to the first current.
  • the first characteristic data includes the first change characteristic in the time domain of the first phase value corresponding to the first current;
  • the first phase value is The phase in the complex signal obtained by decomposing the first current;
  • the first change characteristic is related to the change amplitude of the first phase value in the time domain;
  • the fault determination module is used to determine the fault degree of the motor based on the first characteristic data.
  • the first current is the stator current of the motor in the first time period
  • the acquisition module is also used to:
  • the second current is the stator current of the motor during normal operation or a second time period, and the second time period is the time period before the first time period;
  • Feature extraction module also used for:
  • second characteristic data of the second current is obtained, and the second characteristic data and the first characteristic data are data calculated in the same way;
  • Fault determination module specifically used for:
  • the fault degree of the motor is determined.
  • the second characteristic data includes the second change characteristic in the time domain of the second phase value corresponding to the second current; the second phase value is the phase in the complex signal obtained by decomposing the second current; The second change characteristic is related to the change amplitude of the second phase value in the time domain.
  • the existing fault level is represented by fault level, fault score, or comparison information of the fault level of the electrode with the fault level of other motors.
  • one or more phases of the three-phase power may have partial or abnormal current values (there are obvious value jumps and other abnormal conditions).
  • the corresponding current value of one or two other phases can be used to complete it (because the currents of different phases in three-phase power are only different in phase under normal circumstances, amplitudes are the same).
  • the correlation between currents can be used for signal preprocessing.
  • the amplitudes of aligned phases in multiple phases (for example, two phases or three phases) of three-phase electricity can be fused and used as the first current.
  • a fault detection device which may include a memory, a processor, and a bus system.
  • the memory is used to store programs
  • the processor is used to execute programs in the memory to perform the first aspect as described above. and any optional method thereof, as well as the above second aspect and any optional method thereof.
  • embodiments of the present application provide a computer-readable storage medium.
  • a computer program is stored in the computer-readable storage medium. When it is run on a computer, it causes the computer to execute the above-mentioned first aspect and any of its options. method, as well as the above-mentioned second aspect and any optional method thereof.
  • embodiments of the present application provide a computer program that, when run on a computer, causes the computer to execute the above-mentioned first aspect and any optional method thereof, as well as the above-mentioned second aspect and any optional method thereof. method of selection.
  • this application provides a chip system, which includes a processor for supporting an execution device or a training device to implement the functions involved in the above aspects, for example, sending or processing data involved in the above methods; Or, information.
  • the chip system also includes a memory, which is used to save necessary program instructions and data for executing the device or training the device.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • FIGS 1 and 2 are schematic diagrams of the application system framework of the present invention.
  • Figure 3 is a schematic diagram of an optional hardware structure of the terminal
  • Figure 4 is a schematic structural diagram of a server
  • Figure 5 shows a fault warning diagram
  • Figure 6 shows the process of a cloud service
  • Figure 7 is a schematic diagram of the application system framework of the present invention.
  • Figure 8 is a schematic flowchart of a fault detection method provided by an embodiment of the present application.
  • Figure 9 is a schematic diagram of a product spectrum provided by an embodiment of the present application.
  • Figure 10 is a schematic diagram for determining the degree of fault provided by the embodiment of the present application.
  • Figure 11 is a schematic flowchart of a fault detection method provided by an embodiment of the present application.
  • Figure 12 is a schematic diagram of a fault degree provided by an embodiment of the present application.
  • Figure 13 is a schematic flowchart of a fault detection method provided by an embodiment of the present application.
  • Figures 14 and 15 are schematic structural diagrams of a data processing device provided by embodiments of the present application.
  • Figure 16 is a schematic structural diagram of an execution device provided by an embodiment of the present application.
  • Figure 17 is a schematic structural diagram of the training equipment provided by the embodiment of the present application.
  • Figure 18 is a schematic structural diagram of a chip provided by an embodiment of the present application.
  • the terms “substantially”, “about” and similar terms are used as terms of approximation, not as terms of degree, and are intended to take into account measurements or values that would be known to one of ordinary skill in the art. The inherent bias in calculated values.
  • the use of “may” when describing embodiments of the present invention refers to “one or more possible embodiments.”
  • the terms “use”, “using”, and “used” may be deemed to be the same as the terms “utilize”, “utilizing”, and “utilize”, respectively. Synonymous with “utilized”.
  • the term “exemplary” is intended to refer to an example or illustration.
  • This application can be, but is not limited to, applied in motor fault detection applications or cloud services provided by cloud-side servers. Next, we will introduce them respectively:
  • the product form of the embodiment of this application may be a fault detection application.
  • Fault detection applications can run on terminal devices or cloud-side servers.
  • the fault detection application program can perform the fault detection task of the motor based on the operating data of the motor, wherein the fault detection application program can respond to the input operating data of the motor (such as the stator current of the motor).
  • the user can open a fault detection application installed on the terminal device and input the operating data of the motor.
  • the fault detection application can process the operating data of the motor through the method provided by the embodiment of this application. , and present the fault detection results to the user.
  • the fault detection result may be the extent to which the motor has failed.
  • the user can open a fault detection application installed on the terminal device and input the operating data of the motor.
  • the fault detection application can send the operating data of the motor to the server on the cloud side.
  • the server processes the operating data of the motor through the method provided by the embodiments of this application, and transmits the fault detection results back to the terminal device, and the terminal device can present the fault detection results to the user.
  • the user can open a fault detection application installed on the terminal device and input the motor's operating data.
  • the terminal device where the fault detection application is located can reserve questions corresponding to the motor's operating data in advance. Therefore, the user does not need to actively input.
  • the fault detection application can send the operating data of the motor to the server on the cloud side.
  • the server on the cloud side processes the operating data of the motor through the method provided by the embodiment of this application and sends the fault detection results.
  • the terminal device can present the fault detection results to the user.
  • Figure 1 is a schematic diagram of the functional architecture of a fault detection application in an embodiment of the present application:
  • the fault detection application program 102 can receive input parameters 101 (such as the operating data of the motor) and generate a fault detection result 103 of the operating data of the motor.
  • Fault detection application 102 may execute, for example, on at least one computer system and includes computer code that, when executed by one or more computers, causes the computers to perform operations described herein. fault detection method.
  • Figure 2 is a schematic diagram of the physical architecture of running a fault detection application in an embodiment of the present application:
  • FIG. 2 shows a schematic diagram of a system architecture.
  • the system may include a terminal 100 and a server 200.
  • the server 200 may include one or more servers (one server is used as an example for illustration in FIG. 2), and the server 200 may provide fault detection services for one or more terminals.
  • the terminal 100 can be installed with a fault detection application, or a webpage related to fault detection can be opened.
  • the above application and webpage can provide a fault detection interface, and the terminal 100 can receive relevant parameters input by the user on the fault detection interface, and The above parameters are sent to the server 200.
  • the server 200 can obtain the processing results based on the received parameters and return the processing results to the terminal 100.
  • the terminal 100 can also complete the action of obtaining data processing results based on the received parameters by itself without requiring the cooperation of the server, which is not limited by the embodiments of this application.
  • the terminal 100 in the embodiment of the present application can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR)/virtual reality (VR) device, a notebook computer, or an ultra mobile personal computer (ultra mobile personal computer).
  • - mobile personal computer UMPC
  • netbook personal digital assistant
  • PDA personal digital assistant
  • FIG. 3 shows an optional hardware structure diagram of the terminal 100.
  • the terminal 100 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), Microphone 162 (optional), processor 170, external interface 180, power supply 190 and other components.
  • a radio frequency unit 110 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), Microphone 162 (optional), processor 170, external interface 180, power supply 190 and other components.
  • Figure 3 is only an example of a terminal or a multi-function device, and does not constitute a limitation on the terminal or multi-function device. It may include more or fewer components than shown in the figure, or combine certain components. Or different parts.
  • the input unit 130 may be used to receive input numeric or character information and generate key signal input related to user settings and function control of the portable multi-function device.
  • the input unit 130 may include a touch screen 131 (optional) and/or other input devices 132.
  • the touch screen 131 can collect the user's touch operations on or near it (such as the user's operations on or near the touch screen using fingers, knuckles, stylus, or any other suitable objects), and drive the corresponding according to the preset program. Connect the device.
  • the touch screen can detect the user's touch action on the touch screen, convert the touch action into a touch signal and send it to the processor 170, and can receive and execute commands from the processor 170; the touch signal at least includes contact point coordinate information.
  • the touch screen 131 can provide an input interface and an output interface between the terminal 100 and the user.
  • touch screens can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave.
  • the input unit 130 may also include other input devices.
  • other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys 132, switch keys 133, etc.), trackball, mouse, joystick, etc.
  • the input device 132 may receive input operating data of the motor and the like.
  • the display unit 140 may be used to display information input by the user or information provided to the user, various menus of the terminal 100, interactive interfaces, file display, and/or playback of any kind of multimedia files.
  • the display unit 140 may be used to display the interface of the fault detection application program, fault detection results, etc.
  • the memory 120 can be used to store instructions and data.
  • the memory 120 can mainly include a storage instruction area and a storage data area.
  • the storage data area can store various data, such as multimedia files, text, etc.;
  • the storage instruction area can store operating systems, applications, at least Software units such as instructions required for a function, or their subsets or extensions.
  • Non-volatile random access memory may also be included; providing the processor 170 with management of hardware, software and data resources in the computing processing device and supporting control software and applications. It is also used for storage of multimedia files, as well as storage of running programs and applications.
  • the processor 170 is the control center of the terminal 100. It uses various interfaces and lines to connect various parts of the entire terminal 100, and executes various functions of the terminal 100 by running or executing instructions stored in the memory 120 and calling data stored in the memory 120. functions and process data to provide overall control of the terminal device.
  • the processor 170 may include one or more processing units; preferably, the processor 170 may integrate an application processor and a modem processor, where the application processor mainly processes operating systems, user interfaces, application programs, etc. , the modem processor mainly handles wireless communications. It can be understood that the above modem processor may not be integrated into the processor 170 .
  • the processor and memory can be implemented on a single chip, and in some embodiments, they can also be implemented on separate chips.
  • the processor 170 can also be used to generate corresponding operation control signals, send them to corresponding components of the computing processing device, read and process data in the software, especially read and process the data and programs in the memory 120, so that the Each functional module performs a corresponding function, thereby controlling the corresponding components to act according to the instructions.
  • the memory 120 can be used to store software codes related to the fault detection method, and the processor 170 can execute the steps of the fault detection method of the chip, and can also schedule other units (such as the above-mentioned input unit 130 and the display unit 140) to implement corresponding functions. .
  • the radio frequency unit 110 (optional) can be used to send and receive information or receive and send signals during calls. For example, after receiving downlink information from the base station, it is processed by the processor 170; in addition, the designed uplink data is sent to the base station.
  • RF circuits include, but are not limited to, antennas, at least one amplifier, transceivers, couplers, low noise amplifiers (LNA), duplexers, etc.
  • the radio frequency unit 110 can also communicate with network devices and other devices through wireless communication.
  • the wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (Code Division) Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.
  • GSM Global System of Mobile communication
  • GPRS General Packet Radio Service
  • CDMA Code Division Multiple Access
  • WCDMA Wideband Code Division Multiple Access
  • LTE Long Term Evolution
  • SMS Short Messaging Service
  • the radio frequency unit 110 can send the chip parameters to the server 200 and receive the fault detection result sent by the server 200.
  • radio frequency unit 110 is optional and can be replaced by other communication interfaces, such as a network port.
  • the terminal 100 also includes a power supply 190 (such as a battery) that supplies power to various components.
  • a power supply 190 such as a battery
  • the power supply can be logically connected to the processor 170 through a power management system, so that functions such as charging, discharging, and power consumption management can be implemented through the power management system.
  • the terminal 100 also includes an external interface 180, which can be a standard Micro USB interface or a multi-pin connector, which can be used to connect the terminal 100 to communicate with other devices, or can be used to connect a charger to charge the terminal 100. .
  • an external interface 180 can be a standard Micro USB interface or a multi-pin connector, which can be used to connect the terminal 100 to communicate with other devices, or can be used to connect a charger to charge the terminal 100.
  • the terminal 100 may also include a flash light, a wireless fidelity (WiFi) module, a Bluetooth module, sensors with different functions, etc., which will not be described again here. Some or all of the methods described below may be applied in the terminal 100 shown in FIG. 3 .
  • WiFi wireless fidelity
  • Bluetooth Bluetooth
  • FIG 4 provides a schematic structural diagram of a server 200.
  • the server 200 includes a bus 201, a processor 202, a communication interface 203 and a memory 204.
  • the processor 202, the memory 204 and the communication interface 203 communicate through the bus 201.
  • the bus 201 may be a peripheral component interconnect standard (PCI) bus or an extended industry standard architecture (EISA) bus, etc.
  • PCI peripheral component interconnect standard
  • EISA extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus, etc. For ease of presentation, only one thick line is used in Figure 4, but it does not mean that there is only one bus or one type of bus.
  • the processor 202 may be a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP) or a digital signal processor (DSP). any one or more of them.
  • CPU central processing unit
  • GPU graphics processing unit
  • MP microprocessor
  • DSP digital signal processor
  • Memory 204 may include volatile memory, such as random access memory (RAM).
  • RAM random access memory
  • the memory 204 may also include non-volatile memory (non-volatile memory), such as read-only memory (ROM), flash memory, mechanical hard drive (hard drive drive, HDD) or solid state drive (solid state drive). , SSD).
  • ROM read-only memory
  • HDD hard drive drive
  • SSD solid state drive
  • the memory 204 can be used to store software codes related to the fault detection method, and the processor 202 can execute the steps of the chip's fault detection method, and can also schedule other units to implement corresponding functions.
  • the terminal 100 and the server 200 may be centralized or distributed devices, and the processors (such as the processor 170 and the processor 202) in the terminal 100 and the server 200 may be hardware circuits (such as application specific integrated circuits) application specific integrated circuit (ASIC), field-programmable gate array (FPGA), general-purpose processor, digital signal processing (DSP), microprocessor or microcontroller, etc.), Or a combination of these hardware circuits.
  • the processor can be a hardware system with the function of executing instructions, such as CPU, DSP, etc., or a hardware system without the function of executing instructions, such as ASIC, FPGA, etc., or the above-mentioned processor without the function of executing instructions.
  • the server can provide fault detection services for the client side through an application programming interface (API).
  • API application programming interface
  • the terminal device can send relevant parameters (such as the operating data of the motor) to the server through the API provided by the cloud.
  • the server can obtain the processing results based on the received parameters and use the processing results (such as fault detection of the operating data of the motor) results, etc.) is returned to the terminal.
  • Figure 5 shows the process of using a fault detection cloud service provided by a cloud platform.
  • SDK software development kit
  • the cloud platform provides multiple development versions of SDK for users to choose according to the needs of the development environment, such as JAVA version of SDK and python version. SDK, PHP version SDK, Android version SDK, etc.
  • the SDK project is imported into the local development environment, and configured and debugged in the local development environment.
  • the local development environment can also develop other functions, forming a collection of faults. Application of detection capabilities.
  • API calls for fault detection can be triggered.
  • the application triggers the fault detection function, it initiates an API request to the running instance of the fault detection service in the cloud environment.
  • the API request carries the running data of the motor, and the running instance in the cloud environment processes the running data of the motor. Get fault detection results.
  • the cloud environment returns the fault detection result to the application, thus completing a fault detection service call.
  • Fourier decomposition also known as Fourier transform
  • Fourier transform can express a function as a linear combination of trigonometric functions (sine and/or cosine functions) or their integrals.
  • trigonometric functions sine and/or cosine functions
  • Fourier transform There are many different variations of Fourier transform in different research fields, such as continuous Fourier transform and discrete Fourier transform.
  • the core of Fourier transform is the transformation from time domain to frequency domain, and this transformation is realized through a special set of orthogonal basis.
  • Harmonics refer to components that are greater than integer multiples of the fundamental frequency obtained by Fourier series decomposition of periodic non-sinusoidal alternating currents. They are usually called high-order harmonics, and the fundamental wave refers to its frequency and power frequency. (50Hz) same component.
  • An electric motor is a device that converts electrical energy into mechanical energy. It uses an energized coil (that is, the stator winding) to generate a rotating magnetic field and acts on the rotor (such as a squirrel-cage closed aluminum frame) to form a magneto-electric rotating torque. Motors are divided into DC motors and AC motors according to the power source used. Most of the motors in the power system are AC motors, which can be synchronous motors or asynchronous motors (the stator magnetic field speed of the motor does not maintain the same speed as the rotor rotation speed).
  • the motor is mainly composed of a stator and a rotor.
  • the energized wire moves in the direction of the force in the magnetic field. It is related to the direction of the current and the direction of the magnetic field lines (magnetic field direction).
  • the working principle of the motor is the force exerted by the magnetic field on the current, causing the motor to rotate.
  • AC motor is a machine used to realize the mutual conversion of mechanical energy and AC electric energy. Due to the tremendous development of AC power systems, AC motors have become the most commonly used motors. Compared with DC motors, AC motors have no commutator (see commutation of DC motors), so they have a simple structure, are easy to manufacture, are relatively strong, and can easily be made into high-speed, high-voltage, large-current, and large-capacity motors.
  • Three-phase current passes through three conductors, each conductor serves as a loop for the other two, and the phase difference of its three components is one-third of a cycle or a current with a phase angle of 120°.
  • the stator is the stationary part of the motor.
  • the stator consists of three parts: stator core, stator winding and frame.
  • the function of the stator generates alternating current, and the function of the rotor is to form a rotating magnetic field.
  • the peak-to-peak value refers to the difference between the highest value and the lowest value of the signal within a period, which is the range between the maximum and minimum. It describes the size of the range of changes in signal values.
  • Motors are the most common equipment for driving various machinery in the production process. They are widely used in industrial production, transportation, infrastructure, agricultural development, and daily life. The electricity consumption of motors accounts for 10% of the total production electricity consumption. More than 80%. As an electrical equipment that provides power to many industries, it has many potential failure factors. Downtime due to failures will cause great economic losses. If motor faults can be detected in time and repairs and maintenance are carried out at the early stage of motor failure, the service life of the motor can be effectively extended and the reliability and stability of the entire production system can be improved.
  • the motor's protection settings appear to be perfect, but in actual operation, the relay will only sound an alarm when a motor failure occurs. However, if the motor suddenly loses power or stops running, it will cause huge losses.
  • this method can only be used to detect faults after point A, that is, the point where the functional failure occurs.
  • point A When point A is reached, the equipment completely fails. It is impossible to find point P, point F and point A, that is, the part between the deterioration starting point, the potential fault occurrence point and the functional failure point.
  • point P point F
  • point A point between the deterioration starting point
  • point F point F
  • point A point between the deterioration starting point
  • Figure 7 is an architecture schematic taking an industrial scenario as an example, in which the stator current signal can be installed on the side of the motor electrical control cabinet.
  • the collector collects and reports data; then, the edge side (the edge side is optional, for example, the edge side can be an edge gateway) collects and reports the data; the center side (for example, the server) can perform execution based on the reported data.
  • the fault detection method in the embodiment of the present application and outputs the fault detection result.
  • FIG 8 is a flow diagram of an embodiment of a fault detection method provided by an embodiment of the present application.
  • the fault detection method includes:
  • the relevant operating parameters of the motor can be analyzed.
  • the stator current is a relatively sensitive state parameter inside the motor, and as a non-invasive method
  • the sensing signal is easy to obtain and can be collected directly in the distribution cabinet.
  • the fault degree of the motor can be determined by analyzing the harmonic components of the stator current.
  • a sensor for collecting the stator current on the motor can be provided, for example, a stator current signal collector, and the sensor can collect the stator current of the stator on the motor.
  • a stator current signal collector can be installed on the electric control cabinet side of the motor.
  • the stator current of the motor stator may be three-phase electricity, and the stator current may be one or more phases of the three-phase electricity.
  • the three-phase power may include a first phase current, a second phase current, and a third phase current, respectively corresponding to the U phase, V phase, and W phase in the three phase power.
  • the senor can collect the stator current at a certain frequency.
  • the sampling frequency can be, for example, at least 1K.
  • one or more phases of three-phase power may have partial or abnormal current values (there are obvious value jumps and other abnormal conditions).
  • the corresponding current value of one or two other phases can be used to complete (because the currents of different phases in three-phase power are only different in phase under normal circumstances, the amplitude is identical).
  • the correlation between currents can be used for signal preprocessing.
  • the amplitudes of aligned phases in multiple phases (for example, two phases or three phases) of three-phase electricity can be fused and used as the first current.
  • fusion can be the splicing of amplitudes of different phases, or averaging.
  • current can be the first current
  • c_ ⁇ 1-3 ⁇ represents the current of each phase
  • ⁇ sum_ represents the sum
  • w_i represents the weight. If it is judged to be a non-abnormal value, the weight is 1; if it is an abnormal value, the weight is 0.
  • other preprocessing can be performed on the original signal of the collected current. For example, for missing data, the value that appears most often in the data set can be selected to fill in the corresponding missing data.
  • a normal range band can be given. If the voltage and current data are not within this band, it is regarded as abnormal data and is directly eliminated.
  • the original signal collected may contain noise, and the original signal can be denoised.
  • the wavelet threshold denoising method can be used. First, perform wavelet decomposition on the original signal, select an appropriate wavelet coefficient threshold, and compare the threshold with the high-frequency wavelet coefficients at each decomposition scale. If the wavelet coefficient is greater than the threshold, the wavelet coefficient is retained. Wavelet coefficients, otherwise appropriate thresholding is applied. The threshold-processed wavelet coefficients are subjected to inverse wavelet transformation to obtain the denoised reconstructed signal.
  • the first time period may be a continuous time period or multiple moments within a continuous time period, and the first time period may also be a discontinuous time period or within a discontinuous time period. Multiple moments are not limited here.
  • the first current may be an instantaneous value of the current at each moment in multiple moments within a time period.
  • the first characteristic data is related to the fault of the motor;
  • the first characteristic data is a plurality of the first current. a numerical relationship between a first harmonic amplitude and a plurality of first amplitudes, the plurality of first amplitudes including a first fundamental amplitude of the first current and a plurality of second harmonic amplitudes,
  • the plurality of second harmonic amplitudes have nothing to do with the fault of the motor;
  • the application extracts characteristic data from the signal (stator current) caused by the potential fault of the motor.
  • This characteristic data is the embodiment of abnormal components in the stator current.
  • the degree of potential fault in the motor can be determined based on this characteristic data.
  • Abnormal components in the signal (stator current) caused by potential faults of the motor can be harmonic components or fluctuations in phase values (variation characteristics), which are introduced below:
  • the characteristic data is the harmonic component in the stator current.
  • Harmonic components can also be called harmonic currents. Harmonic currents are the collective name for sinusoidal components whose frequency is an integer multiple of the original periodic current frequency when the non-sinusoidal periodic current function is expanded according to the Fourier series.
  • the first current can be Fourier decomposed to obtain the fundamental wave and multiple harmonics of the first current.
  • the potential fault of the motor can be reflected in one or more of the multiple harmonics.
  • On the wave that is to say, one or more harmonics among the multiple harmonics are related to the potential fault of the motor.
  • the degree of the potential fault of the motor can be directly reflected in one or more of the multiple harmonics. superior.
  • the frequency of harmonics related to potential faults at different structural positions on the motor may be different.
  • potential faults in the bearings of the motor may cause the amplitude of harmonics at 60hz. value increases. Therefore, the amplitudes of the harmonics of the harmonic frequencies corresponding to each structure of the motor can be analyzed (optionally, the amplitudes of all harmonics can also be analyzed). If the amplitudes meet the preset conditions (for example, If the value is greater than the threshold or other conditions), it can be considered as the amplitude of the harmonics related to the potential fault of the motor.
  • harmonic product spectrum is used to accurately extract non-noise harmonic components.
  • the principle is that noise generally only causes a single harmonic, and a fault not only causes harmonics at the fault frequency point, but also causes harmonic components at multiples of the fault frequency.
  • fusion such as product, that is, Eq. (1)
  • the harmonic characteristics related to potential faults of the motor can be amplified and the noise can be removed.
  • the principle of the harmonic product spectrum can be shown in Figure 9. 60Hz and 110Hz are the frequencies of harmonics related to potential faults.
  • the characteristic data includes the amplitude of the fundamental wave of the first current (for example, the amplitude of the first fundamental wave in the embodiment of the present application) and multiple Amplitudes of harmonics (such as multiple first harmonic amplitudes in the embodiments of the present application), wherein multiple first harmonic amplitudes among the multiple first harmonic amplitudes are related to the existence of the motor
  • the amplitude of the harmonic related to the potential fault, and the fusion result of each first harmonic amplitude of the plurality of first harmonic amplitudes and the corresponding plurality of fourth harmonic amplitudes for example, the fusion result
  • the result can be obtained through product operation, neural network, etc.) that meets the preset conditions, or each first harmonic amplitude and the corresponding plurality of fourth harmonics in the plurality of first harmonic amplitudes.
  • Each fourth harmonic amplitude in the amplitude satisfies the preset condition, and each fourth harmonic amplitude is a harmonic of a multiple of the harmonic frequency corresponding to the first harmonic amplitude.
  • Amplitude the preset condition can be that the value is greater than the threshold.
  • the fusion result of each first harmonic amplitude in the plurality of first harmonic amplitudes and the corresponding plurality of fourth harmonic amplitudes (for example, the fusion result can be through product operation, neural network, etc. (obtained in a manner) that satisfies the preset conditions, and each fourth harmonic amplitude is the amplitude of a harmonic that is a multiple of the harmonic frequency corresponding to the first harmonic amplitude.
  • the frequencies of harmonics related to potential faults at different structural positions on the motor are different, and there is a corresponding relationship (the structure of the motor and the harmonic frequency).
  • Different motors have different motor structures, and the correspondence between the structure and the harmonic frequency The relationship may also be different.
  • the corresponding relationship between the structure of the motor and the harmonic frequency can be used as prior information, and it is determined which structures of the motor appear by analyzing whether the harmonic frequency is abnormal. Even if the frequency corresponding to the motor structure is abnormal and does not belong to the corresponding relationship, even if the value is greater than a certain threshold, it is considered not to be the harmonic frequency corresponding to the faulty component. This means that current technology relies on prior information when performing fault detection.
  • the above method can only identify harmonics related to potential faults in the motor and locate which structures of the motor have potential faults. In order to quantify the extent of potential faults in the motor, the harmonic amplitudes related to potential faults can be measured. analyze.
  • the characteristic data may include a plurality of first amplitudes, the plurality of first amplitudes including a first fundamental amplitude of the first current and a plurality of second harmonic amplitudes. value (optionally, the plurality of first amplitudes may also include multiple first harmonic amplitudes), and the second harmonic amplitude may be related to noise such as the operating conditions of the motor, rather than caused by the motor's A plurality of first harmonic amplitudes among the plurality of first harmonic amplitudes caused by a fault are related to potential faults of the motor.
  • the above-mentioned fusion result of multiple first harmonic amplitudes related to the potential fault of the motor can represent the energy related to the potential fault of the motor, and the multiple amplitudes
  • the fusion result of values can represent the total energy, and the numerical relationship between the plurality of first harmonic amplitudes and the plurality of first amplitudes, that is, The numerical relationship between the energy related to potential faults of the motor and the total energy can characterize the degree of potential faults in the motor.
  • the stator current caused by noise such as working conditions
  • the harmonic components related to the fault may be different. That is to say, even if the motor fault degree is the same, the magnitude of the harmonics related to the fault may be different in different motors or under different working conditions.
  • the amplitude of the harmonic current related to the fault is divided between the fundamental wave obtained by decomposing the stator current and the harmonics not related to the fault. The numerical relationship is used as a characteristic representation to determine the degree of fault, which can eliminate the influence of different working conditions or motors on the size of the harmonic current and determine the accurate degree of fault.
  • the above numerical relationship may be a first degree of difference between the first fusion result and the second fusion result.
  • the first fusion result or the second fusion result is obtained by accumulation; the first degree of difference may be a ratio.
  • different motors may have different amplitudes of fundamental waves or harmonics.
  • the characteristic data of the motor in a certain period of time cannot Accurately describe the degree of potential failure of the motor.
  • motor A and motor B the operating environment of motor A is relatively noisy. Therefore, even if the amplitude of the harmonics related to potential faults is larger (that is, the degree of potential faults is higher), When the degree of potential fault is large, it may also be due to the large difference between the amplitude and total energy of the harmonics related to the potential fault that an erroneous conclusion that the degree of potential fault is small may be obtained.
  • the characteristic data of the motor during normal operation or historical operation time period can be used as the benchmark, and the difference between the real-time characteristic data of the motor and the benchmark can be used. Comparison is used to determine the degree of potential faults of the motor, which can then reduce the interference of different motors or the same motor in different operating environments.
  • the plurality of first harmonic amplitudes are the amplitudes of a plurality of harmonics of the first frequency; according to the second degree of difference between the first numerical relationship and the second numerical relationship, Determine the extent of potential faults present in the motor.
  • the first numerical relationship is a numerical relationship between the plurality of first harmonic amplitudes and the plurality of first amplitudes
  • the second numerical relationship is a plurality of third harmonic amplitudes of the second current.
  • the amplitude of the wave; the second time period is the time period before the first time period.
  • the corresponding harmonic energy in the harmonic product spectrum can be calculated as a ratio to the total energy of the signal.
  • the characteristic data is the change characteristics of the phase value of the stator current in the time domain.
  • the characteristic data includes a first change characteristic in the time domain of the first phase value corresponding to the first current; the phase value is a complex signal obtained by decomposing the first current. phase in.
  • the first change characteristic may be related to the change amplitude of the first phase value in the time domain.
  • the change amplitude may be represented by the average of peak-to-peak values.
  • the stationary components in the stator current signal can be separated based on the signal preprocessing method, and then the features can be calculated and extracted.
  • the specific steps can be exemplarily as follows: First, perform signal screening, and perform signal processing. Short-time Fourier transform, observe whether the fluctuation of the main frequency component exceeds a certain threshold (such as 5%), if not, proceed to the next step; signal decomposition: perform empirical mode decomposition (EMD) or set on the signal Empirical mode decomposition (ensemble empirical mode decomposition, EEMD), and extract the stationary component, for example, it can be the first intrinsic mode function (intrinsic mode function, IMF) component, as shown in Figure 11 for details.
  • EMD empirical mode decomposition
  • EEMD ensemble empirical mode decomposition
  • the above-extracted stationary components are processed to obtain the instantaneous phase of the first current at each moment, and then the variation amplitude of the instantaneous phase of the signal (that is, the first current) is obtained.
  • determining the fault degree of the motor failure according to the first change characteristic includes: determining the degree of difference between the first change characteristic and the second change characteristic.
  • the fault degree of the motor failure; the second variable The characteristic is the numerical relationship between the plurality of third harmonic amplitudes of the second current and the plurality of second amplitudes; wherein the plurality of second amplitudes include the first phase value corresponding to the second current.
  • the second change characteristic in the time domain; the second current is the stator current of the motor when no fault occurs, or the stator current in the second time period; the second time period is the first time The time period before the period.
  • the distance dis_hocc that can be obtained in the above manner (such as the degree of difference between the first change feature and the second change feature introduced above, and the difference between the first numerical relationship and the second numerical relationship The second degree of difference), can be used to determine the extent of the potential failure.
  • the distance between n segments of normal signals or historical signals can be used for normal distribution fitting, the mean and standard deviation can be calculated, and the interval of the normal signal distribution of dis_hocc can be calculated to determine the severity of the fault. If it is outside the 1sigma interval, it is a minor fault; outside the 2sigma interval, it is a moderate fault; and outside the 3sigma interval, it is a serious fault.
  • the degree of the existing potential failure may be represented by a potential failure level, such as severe, moderate or minor.
  • the degree of the existing potential fault may be a potential fault score, for example, a value between 0 and 100.
  • the existing potential fault degree can be represented by comparative information between the potential fault degree of the electrode and the potential fault degrees of other motors, such as a ranking of potential fault degrees of the motors.
  • Figure 13 is a flow diagram of a fault detection method provided by an embodiment of the present application. As shown in Figure 13, the fault detection method provided by the present application includes:
  • step 1301 For the specific description of step 1301, please refer to the description of step 801 in the above embodiment, which will not be introduced here.
  • the first characteristic data of the first current obtains the first characteristic data of the first current, where the first characteristic data includes the first change characteristic in the time domain of the first phase value corresponding to the first current;
  • the first phase value is the phase in the complex signal obtained by decomposing the first current;
  • the first change characteristic is related to the change amplitude of the first phase value in the time domain;
  • step 1302 and step 1303 reference may be made to the description of step 802 and step 803 in the above embodiment, which will not be introduced here.
  • the first current is the stator current of the motor during a first time period
  • the method further includes: obtaining a second current, where the second current is the stator current of the motor during normal operation or during the first time period.
  • the stator current in two time periods, the second time period being the time period before the first time period;
  • second characteristic data of the second current is obtained, and the second characteristic data and the first characteristic data are the same type of data;
  • the fault degree of the motor is determined.
  • the second characteristic data includes a second change characteristic in the time domain of a second phase value corresponding to the second current; the second phase value is a decomposition of the second current The phase in the obtained complex signal; the second change characteristic is related to the change amplitude of the second phase value in the time domain.
  • the existing fault degree is represented by fault level, fault score, or comparison information between the fault degree of the electrode and the fault degree of other motors.
  • FIG 14 is a structural representation of a fault detection device provided by an embodiment of the present application.
  • a fault detection device 1400 provided by the present application includes:
  • the acquisition module 1401 is used to acquire the first current, where the first current is the stator current of the motor;
  • the feature extraction module 1402 is used to obtain first feature data of the first current according to the first current, where the first feature data is related to the fault of the motor; the first feature data is the first feature data of the first current.
  • a numerical relationship between a plurality of first harmonic amplitudes of a current and a plurality of first amplitudes, the plurality of first amplitudes including a first fundamental amplitude of the first current and a plurality of second Harmonic amplitude, the plurality of second harmonic amplitudes have nothing to do with the fault of the motor;
  • step 802 For a specific description of the feature extraction module 1402, reference may be made to the description of step 802 in the above embodiment, which will not be introduced here.
  • the fault determination module 1403 is used to determine the fault degree of the motor according to the first characteristic data.
  • fault determination module 1403 For detailed description of the fault determination module 1403, reference may be made to the description of step 803 in the above embodiment, which will not be introduced here.
  • the first current is the stator current of the motor in the first time period
  • the acquisition module is also used to:
  • the second current being the stator current of the motor during normal operation or a second time period, the second time period being a time period before the first time period;
  • the feature extraction module is also used to:
  • second characteristic data of the second current is obtained, and the second characteristic data and the first characteristic data are the same type of data;
  • the fault determination module is specifically used for:
  • the fault degree of the motor is determined.
  • the numerical relationship between the plurality of first harmonic amplitudes and the plurality of first amplitudes includes:
  • the plurality of first harmonic amplitudes are the amplitudes of a plurality of harmonics of the first frequency in the first current
  • the second characteristic data is a numerical relationship between a plurality of third harmonic amplitudes of the second current and a plurality of second amplitudes; the plurality of second amplitudes include a fundamental of the second current.
  • the wave amplitude and multiple harmonic amplitudes; the second current is the stator current of the motor when no fault occurs, or the stator current in the second time period; the multiple third harmonic amplitudes are Amplitudes of harmonics of the plurality of first frequencies in the plurality of second amplitudes.
  • each first harmonic amplitude among the plurality of first harmonic amplitudes, and each corresponding fourth harmonic amplitude among the plurality of fourth harmonic amplitudes Both are within the preset numerical range, and each fourth harmonic amplitude is the amplitude of a harmonic that is a multiple of the harmonic frequency corresponding to the first harmonic amplitude; or,
  • the fusion result of the plurality of first harmonic amplitudes and the corresponding plurality of fourth harmonic amplitudes is within a preset numerical range.
  • the existing fault degree is represented by fault level, fault score, or comparison information between the fault degree of the electrode and the fault degree of other motors.
  • FIG. 15 is a schematic structural diagram of a fault detection device provided by an embodiment of the present application.
  • a fault detection device 1500 provided by the present application includes:
  • the acquisition module 1501 is used to acquire the first current, which is the stator current of the motor;
  • fault determination module 1501 For a specific description of the fault determination module 1501, reference may be made to the description of step 1301 in the above embodiment, which will not be introduced here.
  • the feature extraction module 1502 is configured to obtain first feature data of the first current according to the first current, where the first feature data includes the first phase value corresponding to the first current in the time domain.
  • a change characteristic is the phase in the complex signal obtained by decomposing the first current; the first change characteristic is related to the change amplitude of the first phase value in the time domain;
  • fault determination module 1502 For a specific description of the fault determination module 1502, reference may be made to the description of step 1302 in the above embodiment, which will not be introduced here.
  • the fault determination module 1503 is used to determine the fault degree of the motor according to the first characteristic data.
  • fault determination module 1503 For detailed description of the fault determination module 1503, reference may be made to the description of step 1303 in the above embodiment, which will not be introduced here.
  • the first current is the stator current of the motor in the first time period
  • the acquisition module is also used to:
  • the second current being the stator current of the motor during normal operation or a second time period, the second time period being a time period before the first time period;
  • the feature extraction module is also used to:
  • second characteristic data of the second current is obtained, and the second characteristic data and the first characteristic data are Data of the same type;
  • the fault determination module is specifically used for:
  • the fault degree of the motor is determined.
  • the second characteristic data includes a second change characteristic in the time domain of a second phase value corresponding to the second current; the second phase value is a decomposition of the second current The phase in the obtained complex signal; the second change characteristic is related to the change amplitude of the second phase value in the time domain.
  • the existing fault degree is represented by fault level, fault score, or comparison information between the fault degree of the electrode and the fault degree of other motors.
  • FIG. 16 is a schematic structural diagram of an execution device provided by an embodiment of the present application.
  • the execution device 1600 includes: a receiver 1601, a transmitter 1602, a processor 1603 and a memory 1604 (the number of processors 1603 in the execution device 1600 can be one or more, one processor is taken as an example in Figure 16) , wherein the processor 1603 may include an application processor 16031 and a communication processor 16032.
  • the receiver 1601, the transmitter 1602, the processor 1603, and the memory 1604 may be connected by a bus or other means.
  • Memory 1604 may include read-only memory and random access memory and provides instructions and data to processor 1603 .
  • a portion of memory 1604 may also include non-volatile random access memory (NVRAM).
  • NVRAM non-volatile random access memory
  • the memory 1604 stores processor and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, where the operating instructions may include various operating instructions for implementing various operations.
  • the methods disclosed in the above embodiments of the present application can be applied to the processor 1603 or implemented by the processor 1603.
  • the processor 1603 may be an integrated circuit chip with signal processing capabilities. During the implementation process, each step of the above method can be completed by instructions in the form of hardware integrated logic circuits or software in the processor 1603 .
  • the above-mentioned processor 1603 can be a general processor, a digital signal processor (DSP), a microprocessor or a microcontroller, and can further include an application specific integrated circuit (ASIC), a field programmable Gate array (field-programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA field-programmable gate array
  • the processor 1603 can implement or execute each method, step and logical block diagram disclosed in the embodiment of this application.
  • a general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
  • the steps of the method disclosed in conjunction with the embodiments of the present application can be directly implemented by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other mature storage media in this field.
  • the storage medium is located in the memory 1604.
  • the processor 1603 reads the information in the memory 1604 and completes the steps of the fault detection method provided by the above embodiment in combination with its hardware.
  • the receiver 1601 may be used to receive input numeric or character information and generate signal inputs related to relevant settings and functional controls of the radar system.
  • the transmitter 1602 can be used to output numeric or character information through the first interface; the transmitter 1602 can also be used to send instructions to the disk group through the first interface to modify data in the disk group.
  • FIG. 17 is a schematic structural diagram of the server provided by the embodiment of the present application.
  • the server may have relatively large differences due to different configurations or performances, and may include one or One or more central processing units (CPU) 1717 (e.g., one or more processors) and memory 1732, one or more storage media 1730 (e.g., one or more mass storage devices) storing applications 1742 or data 1744 equipment).
  • the memory 1732 and the storage medium 1730 may be short-term storage or persistent storage.
  • the program stored in the storage medium 1730 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the training device.
  • the central processor 1717 may be configured to communicate with the storage medium 1730 and execute a series of instruction operations in the storage medium 1730 on the server 1700 .
  • Server 1700 may also include one or more power supplies 1726, one or more wired or wireless network interfaces 1750, one or more input and output interfaces 1758, and/or, one or more operating systems 1741, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM and so on.
  • operating systems 1741 such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM and so on.
  • the central processor 1717 is used to execute the data processing method described in the above embodiment.
  • An embodiment of the present application also provides a computer program product that, when run on a computer, causes the computer to execute the above implementation The fault detection method described in the example.
  • Embodiments of the present application also provide a computer-readable storage medium, which stores a program for signal processing. When it is run on a computer, it causes the computer to perform the faults described in the above embodiments. Detection method.
  • the fault detection device may be a chip.
  • the chip includes a processing unit and a communication unit.
  • the processing unit may be a processor, for example.
  • the communication unit may be an input/output interface, a pin or a circuit, for example.
  • the processing unit can execute the computer execution instructions stored in the storage unit, so that the chip in the execution device executes the image enhancement method described in the above embodiment, or so that the chip in the training device executes the image enhancement method described in the above embodiment.
  • the storage unit is a storage unit within the chip, such as a register, cache, etc.
  • the storage unit may also be a storage unit located outside the chip in the wireless access device, such as a read-only memory (read-only memory). only memory, ROM) or other types of static storage devices that can store static information and instructions, random access memory (random access memory, RAM), etc.
  • Figure 18 is a schematic structural diagram of a chip provided by an embodiment of the present application.
  • the chip can be represented as a neural network processor NPU 180.
  • the NPU 180 serves as a co-processor and is mounted to the host CPU (Host CPU). On the host CPU, tasks are allocated.
  • the core part of the NPU is the arithmetic circuit 1803.
  • the arithmetic circuit 1803 is controlled by the controller 1804 to extract the matrix data in the memory and perform multiplication operations.
  • the computing circuit 1803 includes multiple processing units (Process Engine, PE).
  • arithmetic circuit 1803 is a two-dimensional systolic array.
  • the arithmetic circuit 1803 may also be a one-dimensional systolic array or other electronic circuit capable of performing mathematical operations such as multiplication and addition.
  • arithmetic circuit 1803 is a general-purpose matrix processor.
  • the arithmetic circuit obtains the corresponding data of matrix B from the weight memory 1802 and caches it on each PE in the arithmetic circuit.
  • the operation circuit takes matrix A data and matrix B from the input memory 1801 to perform matrix operations, and the partial result or final result of the matrix is stored in an accumulator (accumulator) 1808 .
  • the unified memory 1806 is used to store input data and output data.
  • the weight data directly passes through the storage unit access controller (direct memory access controller, DMAC) 1805, and the DMAC is transferred to the weight memory 1802.
  • Input data is also transferred to unified memory 1806 via DMAC.
  • DMAC direct memory access controller
  • BIU is the Bus Interface Unit, that is, the bus interface unit 1810, which is used for the interaction between the AXI bus and the DMAC and the Instruction Fetch Buffer (IFB) 1809.
  • IFB Instruction Fetch Buffer
  • the bus interface unit 1810 (Bus Interface Unit, BIU for short) is used to fetch the memory 1809 to obtain instructions from the external memory, and is also used for the storage unit access controller 1805 to obtain the original data of the input matrix A or the weight matrix B from the external memory.
  • BIU Bus Interface Unit
  • DMAC is mainly used to transfer the input data in the external memory DDR to the unified memory 1806 or the weight data to the weight memory 1802 or the input data to the input memory 1801 .
  • the vector calculation unit 1807 includes multiple arithmetic processing units, and if necessary, further processes the output of the arithmetic circuit, such as vector multiplication, vector addition, exponential operation, logarithmic operation, size comparison, etc.
  • vector calculation unit 1807 can store the processed output vectors to unified memory 1806 .
  • the vector calculation unit 1807 can apply a linear function and/or a nonlinear function to the output of the operation circuit 1803, such as linear interpolation on the feature plane extracted by the convolution layer, or a vector of accumulated values, to generate an activation value.
  • vector calculation unit 1807 generates normalized values, pixel-wise summed values, or both.
  • the processed output vector can be used as an activation input to the arithmetic circuit 1803, such as for use in a subsequent layer in a neural network.
  • the instruction fetch buffer 1809 connected to the controller 1804 is used to store instructions used by the controller 1804;
  • the unified memory 1806, the input memory 1801, the weight memory 1802 and the fetch memory 1809 are all On-Chip memories. External memory is private to the NPU hardware architecture.
  • the processor mentioned in any of the above-mentioned places may be a general central processing unit, a microprocessor, an ASIC, or an integration of one or more programs used to control the relevant steps of the fault detection method described in the above embodiments. circuit.
  • the device embodiments described above are only illustrative.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physically separate. unit, which can be located in a place, or can be distributed across multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • the connection relationship between modules indicates that there are communication connections between them, which can be specifically implemented as one or more communication buses or signal lines.
  • the present application can be implemented by software plus necessary general hardware. Of course, it can also be implemented by dedicated hardware including dedicated integrated circuits, dedicated CPUs, dedicated memories, Special components, etc. to achieve. In general, all functions performed by computer programs can be easily implemented with corresponding hardware. Moreover, the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits or special-purpose circuits. circuit etc. However, for this application, software program implementation is a better implementation in most cases. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product in essence or that contributes to the existing technology.
  • the computer software product is stored in a readable storage medium, such as a computer floppy disk. , U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., including several instructions to cause a computer device (which can be a personal computer, training device, or network device, etc.) to execute the method of each embodiment of the present application. .
  • a computer device which can be a personal computer, training device, or network device, etc.
  • the computer program product includes one or more computer instructions.
  • the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device.
  • the computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website, computer, training facility, or data center to Transmission to another website, computer, training device or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means.
  • wired such as coaxial cable, optical fiber, digital subscriber line (DSL)
  • wireless such as infrared, wireless, microwave, etc.
  • the computer-readable storage medium may be any available medium that a computer can store, or a data storage device such as a training device, a data center, or other integrated media that contains one or more available media.
  • the available media may be magnetic media (eg, floppy disk, hard disk, magnetic tape), optical media (eg, DVD), or semiconductor media (eg, solid state disk (Solid State Disk, SSD)), etc.

Landscapes

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

Abstract

一种故障检测方法，方法包括：获取电机的第一电流；根据所述第一电流，得到所述第一电流的第一特征数据，所述第一特征数据与所述电机的故障有关；所述第一特征数据为所述第一电流的多个第一谐波幅值与多个第一幅值之间的数值关系，所述多个第一幅值包括所述第一电流的第一基波幅值以及多个第二谐波幅值，所述多个第二谐波幅值与所述电机的故障无关；根据所述第一特征数据，确定所述电机的故障程度。本申请可以基于该特征数据来确定电机存在潜在故障的程度。

Description

一种故障检测方法以及相关装置
本申请要求于2022年08月30日提交中国专利局、申请号为202211048338.5、发明名称为“一种故障检测方法以及相关装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及故障检测领域，尤其涉及一种故障检测的方法以及相关装置。
背景技术
电机是驱动生产过程中各种机械最常见的设备，在工业生产、交通运输、基础建设、农业发展以及日常的普通生活中都得到了大量的使用，电机用电量在总生产用电量占比80％以上。作为一种为多行业提供动力的电气设备，其本身存在着许多潜在的故障因素，由于故障导致的停机停产会带来很大的经济损失。如果可以及时的发现电机的故障情况，在电机发生故障的早期阶段就进行检修及维护，那么就可以有效的延长电机的使用寿命并且提高整个生产体系的可靠性与稳定性。
为了保证电机的稳定运行，通过设定各类传感器来监视电机各种参数数值，如果某些参数值超过了继电器的设定值，那么继电器就会发出警报，必要时将通过电机的切断控制回路直接停止电机的运行，以防止生产事故规模的进一步扩大。
从表面上来看，电机的保护设置看似十分完善，但实际运行过程中继电器只有在电机故障发生时才会发出警报，然而，电机如果突然断电或者停止运行都将造成十分巨大的损失。因此，需要识别出电机存在的潜在故障，应理解，电机存在潜在故障并不是指电机已经发生了故障，是发生故障前显露出来的一种劣化现象。为了能够识别出电机存在的潜在故障，亟需一种能够确定电机故障程度的方法，能够识别出电机的潜在故障。
发明内容
本申请提供了一种故障检测方法，可以确定出电机存在潜在故障的程度。
本申请第一方面提供了一种故障检测方法，方法包括：获取第一电流，第一电流为电机的定子电流；根据第一电流，得到第一电流的第一特征数据，第一特征数据与电机的故障有关；第一特征数据为第一电流的多个第一谐波幅值与多个第一幅值之间的数值关系，多个第一幅值包括第一电流的第一基波幅值以及多个第二谐波幅值，多个第一谐波幅值与电机的故障有关，多个第二谐波幅值与电机的故障无关；根据第一特征数据，确定电机的故障程度。
针对于不同电机、或者同一个电机在不同的工况等运行环境下，由于工况等噪声导致的定子电流中的和故障相关的谐波分量可能会不同，也就是说，即使电机的故障程度相同，不同电机或者不同的工况下，和故障相关的谐波的大小也可能不同。为了消除不同工况或者电机的不同对于谐波电流大小的影响，本申请中，根据和故障相关的谐波电流的幅值和对定子电流分解得到的基波以及和故障无关的谐波作为特征表示来进行故障程度的确定，可以消除不同工况或者电机的不同对于谐波电流大小的影响而确定出准确的故障程度。
在一种可能的实现中，为了检测电机的故障，可以对电机运行时的相关运行参数进行分析，电机的运行参数中，定子电流是电机内部相对敏感的状态参数，且作为一种非侵入式传感信号容易获取，可以在配电柜直接采集。本申请实施例中，可以通过对定子电流的谐波成分进行分析，来对电机的故障程度进行确定。在电机出现潜在故障时，会引起电机磁场的气息的不均匀，上述现象会直接表现在定子电流上，例如：电流中会出现明显谐波成分或者是相位值的波动出现不稳定的情况，本申请中提取电机的潜在故障所引起的信号(定子电流)中的特征数据，该特征数据为定子电流中的异常成分的体现，可以基于该特征数据来确定电机存在潜在故障的程度。
在一些情况下，三相电中的一相或多相电可能会存在电流值部分或者异常的情况(存在明显的数值跳变等不正常状态)，为了提高所采集的定子电流的准确性，针对于某一相电流的缺失部分或者异常部分，可以使用其他一相或者两相的相应电流值进行补全(由于三相电中不同相的电流在正常情况下仅仅是相位不同，幅值是相同的)。例如，如果采集了多相电流，可以利用电流间的相关性来进行信号预处理。例如，可以采用三相电中的多相(例如两相或者三相)中对齐相位的幅值进行融合来作为第一电流。
示例性的，融合可以为不同相的幅值相互之间的拼接，或者是求均值。
在一种可能的实现中，所述多个第一谐波幅值与所述多个第一幅值之间的数值关系，包括：第一融合结果和第二融合结果之间的第一差异程度；所述第一融合结果为所述多个第一谐波幅值的融合结果；所述第二融合结果为所述多个第一幅值的融合结果。
其中，上述与电机的潜在故障有关的多个第一谐波幅值的融合结果(例如本申请实施例中的第一融合结果)可以表示电机的潜在故障相关的能量，而多个幅值的融合结果(例如本申请实施例中的第二融合结果)可以表示总能量(例如是包括和故障相关的能量的总能量、或者是除去和故障相关的能量之外的总能量)，而多个第一谐波幅值与多个第一幅值之间的数值关系，也就是电机的潜在故障相关的能量和总能量之间的数值关系，则可以表征出电机存在的潜在故障程度。
在一种可能的实现中，所述第一电流为电机在第一时间段内的定子电流，所述方法还包括：获取第二电流，所述第二电流为所述电机在正常运行或者第二时间段内的定子电流，所述第二时间段为所述第一时间段之前的时间段；所述根据所述第一特征数据，确定所述电机的故障程度，包括：根据所述第二电流，得到所述第二电流的第二特征数据，所述第二特征数据和所述第一特征数据为通过相同方式计算得到的数据；根据所述第一特征数据和所述第二特征数据之间的差异，确定所述电机的故障程度。
在一种可能的实现中，第一时间段可以为连续的时间段或者是连续的时间段内的多个时刻，第一时间段也可以为不连续的时间段或者是不连续的时间段内的多个时刻，这里并不限定。例如，第一电流可以为一个时间段内多个时刻中每个时刻的电流瞬时值。
在一种可能的实现中，不同的电机、或者相同电机在不同的运行环境中，基波或者谐波的幅值都可能是不同的，仅仅利用电机在某个时间段内的特征数据并不能准确的描述出电机的潜在故障程度。
本申请中，为了能够适配于不同的电机、或者不同的电机运行环境，可以将电机在正常运行或者是历史运行时间段内的特征数据作为基准，利用电机实时的特征数据和基准之间的比较，来确定电机的潜在故障程度，进而可以降低不同的电机、或者相同电机在不同的运行环境的差异的干扰。
在一种可能的实现中，所述第二特征数据和所述第一特征数据为通过相同方式计算得到的数据，具体的，所述多个第一谐波幅值为所述第一电流中多个第一频率的谐波的幅值；所述第二特征数据为所述第二电流中所述多个第一频率的谐波的多个第三谐波幅值与多个第二幅值之间的数值关系；所述多个第三谐波幅值为所述第二电流中所述多个第一频率的谐波的幅值，所述多个第二幅值包括所述第二电流的基波幅值以及多个与所述电机的故障无关的谐波幅值；所述第二电流为所述电机在未发生故障的定子电流、或者在第二时间段内的定子电流。
在一种可能的实现中，多个第一谐波幅值中的每个第一谐波幅值、以及对应的多个第四谐波幅值中的每个第四谐波幅值均在预设的数值范围内，每个第四谐波幅值为第一谐波幅值对应的谐波频率的一个倍频的谐波的幅值；或者，多个第一谐波幅值与对应的多个第四谐波幅值的融合结果在预设的数值范围内。
由于并不是所有的谐波都和电机存在的潜在故障有关，有一些谐波是电机正常运行时也会存在的(例如由于电机运行的工况所导致的)，为了分析出电机存在的潜在故障的程度，可以识别出多个谐波中哪些谐波是和电机存在的潜在故障有关的。
然而，由于受到电机运行环境等因素，可能会存在一些谐波幅值满足上述预设条件，但却不是由于 电机的潜在故障所导致的，而是由电机运行环境所导致的，进而引起误判。为了解决这个问题，本申请实施例中，采用谐波乘积谱，能够准确的提取出非噪声的谐波成分。其原理是，噪声一般情况下只会引起单次谐波，而故障除了引起故障频率点的谐波外，在故障频率倍频位置也会引起谐波成分，通过融合，可以将和电机潜在故障相关的谐波特征进行放大，且将噪声进行去除。
也就是说，对第一电流进行处理后，可以得到第一电流的特征数据，特征数据包括第一电流的基波的幅值(例如本申请实施例中的第一基波幅值)和多个谐波的幅值(例如本申请实施例中的多个第一谐波幅值)，其中，多个第一谐波幅值中的多个第一谐波幅值是和电机存在的潜在故障有关的谐波的幅值，且多个第一谐波幅值中的每个第一谐波幅值与对应的多个第四谐波幅值的融合结果(例如，融合结果可以是通过乘积运算、神经网络等方式得到的)满足预设条件，或者是多个第一谐波幅值中的每个第一谐波幅值以及对应的多个第四谐波幅值中的每个第四谐波幅值均满足预设条件，每个第四谐波幅值为第一谐波幅值对应的谐波频率的一个倍频的谐波的幅值，预设条件可以是数值大于阈值。通过上述方式，可以去除由于电机运行环境等因素所导致的误判，进而准确识别出和电机的潜在故障相关的谐波。
其中，多个第一谐波幅值中的每个第一谐波幅值与对应的多个第四谐波幅值的融合结果(例如，融合结果可以是通过乘积运算、神经网络等方式得到的)满足预设条件，每个第四谐波幅值为第一谐波幅值对应的谐波频率的一个倍频的谐波的幅值。通过上述方式，可以去除由于电机运行环境等因素所导致的误判，进而准确识别出和电机的潜在故障相关的谐波。
此外，电机上不同结构的位置存在潜在故障相关的谐波的频率是不同的，且存在对应关系(电机的结构和谐波频率)，不同电机具备不同的电机结构，结构和谐波频率的对应关系也可能不同，现有技术中，针对于不同的电机，可以将该电机的结构和谐波频率之间的对应关系作为先验信息，通过分析谐波频率是否异常来确定电机的哪些结构出现异常，而不属于该对应关系中电机结构对应的频率即使数值大于一定的阈值，也认为其不是故障部件对应的谐波频率。也就是说现在技术在进行故障检测时依赖先验信息。本申请实施例中，由于不需要定位出电机的哪些部件存在故障，仅仅需要确定出哪些频率的谐波是和故障相关的，通过上述倍频谐波的数值判断方法，则可以在不依赖于先验信息的情况下，准确判断出哪些部件存在故障。
在一种可能的实现中，存在的潜在故障程度可以通过潜在故障级别表示，例如严重、中等或者轻微。
在一种可能的实现中，存在的潜在故障程度可以通过潜在故障分数，例如0到100之间的一个数值。
在一种可能的实现中，存在的潜在故障程度可以通过电极的潜在故障程度与其他电机的潜在故障程度的对比信息表示，例如电机潜在故障程度的排名。
第二方面，本申请提供了一种故障检测方法，方法包括：获取第一电流，第一电流为电机的定子电流；根据第一电流，得到第一电流的第一特征数据，第一特征数据包括第一电流对应的第一相位值在时域上的第一变化特征；第一相位值为将第一电流分解得到的复数信号中的相位；第一变化特征与第一相位值在时域上的变化幅度有关；根据第一特征数据，确定电机的故障程度。
在一种可能的实现中，特征数据包括第一电流对应的第一相位值在时域上的第一变化特征；相位值为将第一电流分解得到的复数信号中的相位。可选的，第一变化特征可以与第一相位值在时域上的变化幅度有关，例如，该变化幅度可以通过峰峰值的均值表示。
在一种可能的实现中，第一电流为电机在第一时间段内的定子电流，方法还包括：获取第二电流，第二电流为电机在正常运行或者第二时间段内的定子电流，第二时间段为第一时间段之前的时间段；根据第一特征数据，确定电机的故障程度，包括：根据第二电流，得到第二电流的第二特征数据，所述第二特征数据和所述第一特征数据为通过相同方式计算得到的数据；根据第一特征数据和第二特征数据之间的差异，确定电机的故障程度。
在一种可能的实现中，第二特征数据包括第二电流对应的第二相位值在时域上的第二变化特征；第 二相位值为将第二电流分解得到的复数信号中的相位；第二变化特征与第二相位值在时域上的变化幅度有关。
在一种可能的实现中，存在的故障程度通过故障级别、故障分数或者电极的故障程度与其他电机的故障程度的对比信息表示。
第三方面，本申请提供了一种故障检测装置，装置包括：
获取模块，用于获取第一电流，第一电流为电机的定子电流；
特征提取模块，用于根据第一电流，得到第一电流的第一特征数据，第一特征数据与电机的故障有关；第一特征数据为第一电流的多个第一谐波幅值与多个第一幅值之间的数值关系，多个第一幅值包括第一电流的第一基波幅值以及多个第二谐波幅值，多个第二谐波幅值与电机的故障无关；
故障确定模块，用于根据第一特征数据，确定电机的故障程度。
在一种可能的实现中，第一电流为电机在第一时间段内的定子电流，获取模块，还用于：
获取第二电流，第二电流为电机在正常运行或者第二时间段内的定子电流，第二时间段为第一时间段之前的时间段；
特征提取模块，还用于：
根据所述第二电流，得到所述第二电流的第二特征数据，所述第二特征数据和所述第一特征数据为通过相同方式计算得到的数据；
故障确定模块，具体用于：
根据第一特征数据和第二特征数据之间的差异，确定电机的故障程度。
在一种可能的实现中，多个第一谐波幅值与多个第一幅值之间的数值关系，包括：
第一融合结果和第二融合结果之间的第一差异程度；第一融合结果为多个第一谐波幅值的融合结果；第二融合结果为多个第一幅值的融合结果。
在一种可能的实现中，多个第一谐波幅值为第一电流中多个第一频率的谐波的幅值；
第二特征数据为第二电流的多个第三谐波幅值与多个第二幅值之间的数值关系；多个第二幅值包括第二电流的基波幅值以及多个谐波幅值；第二电流为电机在未发生故障的定子电流、或者在第二时间段内的定子电流；多个第三谐波幅值为多个第二幅值中多个第一频率的谐波的幅值。
在一种可能的实现中，多个第一谐波幅值中的每个第一谐波幅值、以及对应的多个第四谐波幅值中的每个第四谐波幅值均在预设的数值范围内，每个第四谐波幅值为第一谐波幅值对应的谐波频率的一个倍频的谐波的幅值；或者，
多个第一谐波幅值与对应的多个第四谐波幅值的融合结果在预设的数值范围内。
在一种可能的实现中，存在的故障程度通过故障级别、故障分数或者电极的故障程度与其他电机的故障程度的对比信息表示。
第四方面，本申请提供了一种故障检测装置，装置包括：
获取模块，用于获取第一电流，第一电流为电机的定子电流；
特征提取模块，用于根据第一电流，得到第一电流的第一特征数据，第一特征数据包括第一电流对应的第一相位值在时域上的第一变化特征；第一相位值为将第一电流分解得到的复数信号中的相位；第一变化特征与第一相位值在时域上的变化幅度有关；
故障确定模块，用于根据第一特征数据，确定电机的故障程度。
在一种可能的实现中，第一电流为电机在第一时间段内的定子电流，获取模块，还用于：
获取第二电流，第二电流为电机在正常运行或者第二时间段内的定子电流，第二时间段为第一时间段之前的时间段；
特征提取模块，还用于：
根据所述第二电流，得到所述第二电流的第二特征数据，所述第二特征数据和所述第一特征数据为通过相同方式计算得到的数据；
故障确定模块，具体用于：
根据第一特征数据和第二特征数据之间的差异，确定电机的故障程度。
在一种可能的实现中，第二特征数据包括第二电流对应的第二相位值在时域上的第二变化特征；第二相位值为将第二电流分解得到的复数信号中的相位；第二变化特征与第二相位值在时域上的变化幅度有关。
在一种可能的实现中，存在的故障程度通过故障级别、故障分数或者电极的故障程度与其他电机的故障程度的对比信息表示。
在一种可能的实现中，三相电中的一相或多相电可能会存在电流值部分或者异常的情况(存在明显的数值跳变等不正常状态)，为了提高所采集的定子电流的准确性，针对于某一相电流的缺失部分或者异常部分，可以使用其他一相或者两相的相应电流值进行补全(由于三相电中不同相的电流在正常情况下仅仅是相位不同，幅值是相同的)。例如，如果采集了多相电流，可以利用电流间的相关性来进行信号预处理。例如，可以采用三相电中的多相(例如两相或者三相)中对齐相位的幅值进行融合来作为第一电流。
第五方面，本申请实施例提供了一种故障检测设备，可以包括存储器、处理器以及总线系统，其中，存储器用于存储程序，处理器用于执行存储器中的程序，以执行如上述第一方面及其任一可选的方法、以及如上述第二方面及其任一可选的方法。
第六方面，本申请实施例提供了一种计算机可读存储介质，计算机可读存储介质中存储有计算机程序，当其在计算机上运行时，使得计算机执行上述第一方面及其任一可选的方法、以及如上述第二方面及其任一可选的方法。
第七方面，本申请实施例提供了一种计算机程序，当其在计算机上运行时，使得计算机执行上述第一方面及其任一可选的方法、以及如上述第二方面及其任一可选的方法。
第八方面，本申请提供了一种芯片系统，该芯片系统包括处理器，用于支持执行设备或训练设备实现上述方面中所涉及的功能，例如，发送或处理上述方法中所涉及的数据；或，信息。在一种可能的设计中，芯片系统还包括存储器，存储器，用于保存执行设备或训练设备必要的程序指令和数据。该芯片系统，可以由芯片构成，也可以包括芯片和其他分立器件。
附图说明
图1和图2为本发明的应用系统框架示意；
图3为终端的一种可选的硬件结构示意图；
图4为一种服务器的结构示意图；
图5为一种故障预警示意；
图6为一种云服务的流程；
图7为本发明的应用系统框架示意；
图8为本申请实施例提供的一种故障检测方法的流程示意；
图9为本申请实施例提供的一乘积谱示意；
图10为本申请实施例提供的一个故障程度确定示意；
图11为本申请实施例提供的一种故障检测方法的流程示意；
图12为本申请实施例提供的一种故障程度的示意；
图13为本申请实施例提供的一种故障检测方法的流程示意；
图14和图15为本申请实施例提供的数据处理装置的一种结构示意图；
图16为本申请实施例提供的执行设备的一种结构示意图；
图17为本申请实施例提供的训练设备一种结构示意图；
图18为本申请实施例提供的芯片的一种结构示意图。
具体实施方式
下面结合本发明实施例中的附图对本发明实施例进行描述。本发明的实施方式部分使用的术语仅用于对本发明的具体实施例进行解释，而非旨在限定本发明。
本申请的说明书和权利要求书及上述附图中的术语“第一”、第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的术语在适当情况下可以互换，这仅仅是描述本申请的实施例中对相同属性的对象在描述时所采用的区分方式。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，以便包含一系列单元的过程、方法、系统、产品或设备不必限于那些单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它单元。
本文中所用用语“基本(substantially)”、“大约(about)”及类似用语用作近似用语、而并非用作程度用语，且旨在考虑到所属领域中的普通技术人员将知的测量值或计算值的固有偏差。此外，在阐述本发明实施例时使用“可(may)”是指“可能的一个或多个实施例”。本文中所用用语“使用(use)”、“正使用(using)”、及“被使用(used)”可被视为分别与用语“利用(utilize)”、“正利用(utilizing)”、及“被利用(utilized)”同义。另外，用语“示例性(exemplary)”旨在指代实例或例示。
首先介绍本申请的应用场景，本申请可以但不限于应用在电机类的故障检测应用程序或者云侧服务器提供的云服务等，接下来分别进行介绍：
一、故障检测类应用程序
本申请实施例的产品形态可以为故障检测类应用程序。故障检测类应用程序可以运行在终端设备或者云侧的服务器上。
在一种可能的实现中，故障检测类应用程序可以实现基于电机的运行数据执行电机的故障检测任务，其中，故障检测类应用程序可以响应于输入的电机的运行数据(例如电机的定子电流)。
在一种可能的实现中，用户可以打开终端设备上安装的故障检测类应用程序，并输入电机的运行数据，故障检测类应用程序可以通过本申请实施例提供的方法对电机的运行数据进行处理，并将故障检测结果呈现给用户。
例如，故障检测结果可以为电机发生故障的程度。
在一种可能的实现中，用户可以打开终端设备上安装的故障检测类应用程序，并输入电机的运行数据，故障检测类应用程序可以将电机的运行数据发送至云侧的服务器，云侧的服务器通过本申请实施例提供的方法对电机的运行数据进行处理，并将故障检测结果回传至终端设备，终端设备可以将故障检测结果呈现给用户。
在一种可能的实现中，用户可以打开终端设备上安装的故障检测类应用程序，并输入电机的运行数据，故障检测类应用程序所在的终端设备可以预先保留有电机的运行数据对应的题目，因此用户可以不用主动输入，故障检测类应用程序可以将电机的运行数据发送至云侧的服务器，云侧的服务器通过本申请实施例提供的方法对电机的运行数据进行处理，并将故障检测结果回传至终端设备，终端设备可以将故障检测结果呈现给用户。
接下来分别从功能架构以及实现功能的产品架构介绍本申请实施例中的故障检测类应用程序。
参照图1，图1为本申请实施例中故障检测类应用程序的功能架构示意：
在一种可能的实现中，如图1所示，故障检测类应用程序102可接收输入的参数101(例如电机的运行数据)且产生电机的运行数据的故障检测结果103。故障检测类应用程序102可在(举例来说)至少一个计算机系统上执行，且包括计算机代码，所述计算机代码在由一或多个计算机执行时致使所述计算机执行用于执行本文中所描述的故障检测方法。
参照图2，图2为本申请实施例中运行故障检测类应用程序的实体架构示意：
参见图2，图2示出了一种系统架构示意图。该系统可以包括终端100、以及服务器200。其中，服务器200可以包括一个或者多个服务器(图2中以包括一个服务器作为示例进行说明)，服务器200可以为一个或者多个终端提供故障检测服务。
其中，终端100上可以安装有故障检测应用程序，或者打开与故障检测相关的网页，上述应用程序和网页可以提供一个故障检测界面，终端100可以接收用户在故障检测界面上输入的相关参数，并将上述参数发送至服务器200，服务器200可以基于接收到的参数，得到处理结果，并将处理结果返回至至终端100。
应理解，在一些可选的实现中，终端100也可以由自身完成基于接收到的参数，得到数据处理结果的动作，而不需要服务器配合实现，本申请实施例并不限定。
接下来描述图2中终端100的产品形态；
本申请实施例中的终端100可以为手机、平板电脑、可穿戴设备、车载设备、增强现实(augmented reality，AR)/虚拟现实(virtual reality，VR)设备、笔记本电脑、超级移动个人计算机(ultra-mobile personal computer，UMPC)、上网本、个人数字助理(personal digital assistant，PDA)等，本申请实施例对此不作任何限制。
图3示出了终端100的一种可选的硬件结构示意图。
参考图3所示，终端100可以包括射频单元110、存储器120、输入单元130、显示单元140、摄像头150(可选的)、音频电路160(可选的)、扬声器161(可选的)、麦克风162(可选的)、处理器170、外部接口180、电源190等部件。本领域技术人员可以理解，图3仅仅是终端或多功能设备的举例，并不构成对终端或多功能设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件。
输入单元130可用于接收输入的数字或字符信息，以及产生与该便携式多功能装置的用户设置以及功能控制有关的键信号输入。具体地，输入单元130可包括触摸屏131(可选的)和/或其他输入设备132。该触摸屏131可收集用户在其上或附近的触摸操作(比如用户使用手指、关节、触笔等任何适合的物体在触摸屏上或在触摸屏附近的操作)，并根据预先设定的程序驱动相应的连接装置。触摸屏可以检测用户对触摸屏的触摸动作，将该触摸动作转换为触摸信号发送给该处理器170，并能接收该处理器170发来的命令并加以执行；该触摸信号至少包括触点坐标信息。该触摸屏131可以提供该终端100和用户之间的输入界面和输出界面。此外，可以采用电阻式、电容式、红外线以及表面声波等多种类型实现触摸屏。除了触摸屏131，输入单元130还可以包括其他输入设备。具体地，其他输入设备132可以包括但不限于物理键盘、功能键(比如音量控制按键132、开关按键133等)、轨迹球、鼠标、操作杆等中的一种或多种。
其中，输入设备132可以接收到输入的电机的运行数据等等。
该显示单元140可用于显示由用户输入的信息或提供给用户的信息、终端100的各种菜单、交互界面、文件显示和/或任意一种多媒体文件的播放。在本申请实施例中，显示单元140可用于显示故障检测应用程序的界面、故障检测结果等。
该存储器120可用于存储指令和数据，存储器120可主要包括存储指令区和存储数据区，存储数据区可存储各种数据，如多媒体文件、文本等；存储指令区可存储操作系统、应用、至少一个功能所需的指令等软件单元，或者他们的子集、扩展集。还可以包括非易失性随机存储器；向处理器170提供包括管理计算处理设备中的硬件、软件以及数据资源，支持控制软件和应用。还用于多媒体文件的存储，以及运行程序和应用的存储。
处理器170是终端100的控制中心，利用各种接口和线路连接整个终端100的各个部分，通过运行或执行存储在存储器120内的指令以及调用存储在存储器120内的数据，执行终端100的各种功能和处理数据，从而对终端设备进行整体控制。可选的，处理器170可包括一个或多个处理单元；优选的，处理器170可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作系统、用户界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器170中。在一些实施例中，处理器、存储器、可以在单一芯片上实现，在一些实施例中，他们也可以在独立的芯片上分别实现。处理器170还可以用于产生相应的操作控制信号，发给计算处理设备相应的部件，读取以及处理软件中的数据，尤其是读取和处理存储器120中的数据和程序，以使其中的各个功能模块执行相应的功能，从而控制相应的部件按指令的要求进行动作。
其中，存储器120可以用于存储故障检测方法相关的软件代码，处理器170可以执行芯片的故障检测方法的步骤，也可以调度其他单元(例如上述输入单元130以及显示单元140)以实现相应的功能。
该射频单元110(可选的)可用于收发信息或通话过程中信号的接收和发送，例如，将基站的下行信息接收后，给处理器170处理；另外，将设计上行的数据发送给基站。通常，RF电路包括但不限于天线、至少一个放大器、收发信机、耦合器、低噪声放大器(Low Noise Amplifier，LNA)、双工器等。此外，射频单元110还可以通过无线通信与网络设备和其他设备通信。该无线通信可以使用任一通信标准或协议，包括但不限于全球移动通讯系统(Global System of Mobile communication，GSM)、通用分组无线服务(General Packet Radio Service，GPRS)、码分多址(Code Division Multiple Access，CDMA)、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)、长期演进(Long Term Evolution，LTE)、电子邮件、短消息服务(Short Messaging Service，SMS)等。
其中，在本申请实施例中，该射频单元110可以将芯片的参数发送至服务器200，并接收到服务器200发送的故障检测结果。
应理解，该射频单元110为可选的，其可以被替换为其他通信接口，例如可以是网口。
终端100还包括给各个部件供电的电源190(比如电池)，优选的，电源可以通过电源管理系统与处理器170逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。
终端100还包括外部接口180，该外部接口可以是标准的Micro USB接口，也可以使多针连接器，可以用于连接终端100与其他装置进行通信，也可以用于连接充电器为终端100充电。
尽管未示出，终端100还可以包括闪光灯、无线保真(wireless fidelity，WiFi)模块、蓝牙模块、不同功能的传感器等，在此不再赘述。下文中描述的部分或全部方法均可以应用在如图3所示的终端100中。
接下来描述图2中服务器200的产品形态；
图4提供了一种服务器200的结构示意图，如图4所示，服务器200包括总线201、处理器202、通信接口203和存储器204。处理器202、存储器204和通信接口203之间通过总线201通信。
总线201可以是外设部件互连标准(peripheral component interconnect，PCI)总线或扩展工业标准结构(extended industry standard architecture，EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示，图4中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
处理器202可以为中央处理器(central processing unit，CPU)、图形处理器(graphics processing unit，GPU)、微处理器(micro processor，MP)或者数字信号处理器(digital signal processor，DSP)等处理器中的任意一种或多种。
存储器204可以包括易失性存储器(volatile memory)，例如随机存取存储器(random access memory，RAM)。存储器204还可以包括非易失性存储器(non-volatile memory)，例如只读存储器(read-only memory，ROM)，快闪存储器，机械硬盘(hard drive drive，HDD)或固态硬盘(solid state drive，SSD)。
其中，存储器204可以用于存储故障检测方法相关的软件代码，处理器202可以执行芯片的故障检测方法的步骤，也可以调度其他单元以实现相应的功能。
应理解，上述终端100和服务器200可以为集中式或者是分布式的设备，上述终端100和服务器200中的处理器(例如处理器170以及处理器202)可以为硬件电路(如专用集成电路(application specific integrated circuit，ASIC)、现场可编程门阵列(field-programmable gate array，FPGA)、通用处理器、数字信号处理器(digital signal processing，DSP)、微处理器或微控制器等等)、或这些硬件电路的组合，例如，处理器可以为具有执行指令功能的硬件系统，如CPU、DSP等，或者为不具有执行指令功能的硬件系统，如ASIC、FPGA等，或者为上述不具有执行指令功能的硬件系统以及具有执行指令功能的硬件系统的组合。
二、服务器提供的故障检测类云服务：
在一种可能的实现中，服务器可以通过应用程序编程接口(application programming interface，API)为端侧提供故障检测的服务。
其中，终端设备可以通过云端提供的API，将相关参数(例如电机的运行数据)发送至服务器，服务器可以基于接收到的参数，得到处理结果，并将处理结果(例如电机的运行数据的故障检测结果等)返回至至终端。
关于终端以及服务器的描述可以上述实施例的描述，这里不再赘述。
如图5示出了使用一项云平台提供的故障检测类云服务的流程。
1.开通并购买内容审核服务。
2.用户可以下载内容审核服务对应的软件开发工具包(software development kit，SDK)，通常云平台提供多个开发版本的SDK，供用户根据开发环境的需求选择，例如JAVA版本的SDK、python版本的SDK、PHP版本的SDK、Android版本的SDK等。
3.用户根据需求下载对应版本的SDK到本地后，将SDK工程导入至本地开发环境，在本地开发环境中进行配置和调试，本地开发环境还可以进行其他功能的开发，使得形成一个集合了故障检测类能力的应用。
4.故障检测类应用在被使用的过程中，当需要进行故障检测时，可以触发故障检测的API调用。当应用触发故障检测功能时，发起API请求至云环境中的故障检测类服务的运行实例，其中，API请求中携带电机的运行数据，由云环境中的运行实例对电机的运行数据进行处理，获得故障检测结果。
5.云环境将故障检测结果返回至应用，由此完成一次的故障检测服务调用。
关于终端以及服务器的描述可以上述实施例的描述，这里不再赘述。
本申请实施例涉及了许多关于故障检测的相关知识，为了更好地理解本申请实施例的方案，下面先对本申请实施例可能涉及的相关术语和概念进行介绍。应理解的是，相关的概念解释可能会因为本申请实施例的具体情况有所限制，但并不代表本申请仅能局限于该具体情况，在不同实施例的具体情况可能也会存在差异，具体此处不做限定。
(1)傅里叶分解
傅立叶分解也可以称之为傅里叶变换，能将某个函数表示成三角函数(正弦和/或余弦函数)或者它们的积分的线性组合。在不同的研究领域，傅立叶变换具有多种不同的变体形式，如连续傅立叶变换和离散傅立叶变换。傅里叶变换的核心是从时域到频域的变换，而这种变换是通过一组特殊的正交基来实现的。
(2)谐波和基波
谐波是指对周期性非正弦交流量进行傅里叶级数分解所得到的大于基波频率整数倍的各次分量，通常称为高次谐波，而基波是指其频率与工频(50Hz)相同的分量。
(3)电机
电动机是把电能转换成机械能的一种设备。它是利用通电线圈(也就是定子绕组)产生旋转磁场并作用于转子(如鼠笼式闭合铝框)形成磁电动力旋转扭矩。电动机按使用电源不同分为直流电动机和交流电动机，电力系统中的电动机大部分是交流电机，可以是同步电机或者是异步电机(电机定子磁场转速与转子旋转转速不保持同步速)。电动机主要由定子与转子组成，通电导线在磁场中受力运动的方向 跟电流方向和磁感线(磁场方向)方向有关。电动机工作原理是磁场对电流受力的作用，使电动机转动。
(4)交流电机
“交流电机”是用于实现机械能和交流电能相互转换的机械。由于交流电力系统的巨大发展，交流电机已成为最常用的电机。交流电机与直流电机相比，由于没有换向器(见直流电机的换向)，因此结构简单，制造方便，比较牢固，容易做成高转速、高电压、大电流、大容量的电机。
(5)三相电流
三相电流是通过三根导线,每根导线作为其他两根的回路,其三个分量的相位差依次为一个周期的三分之一或120°相位角的电流。
(6)定子
定子是电动机静止不动的部分。定子由定子铁芯、定子绕组和机座三部分组成。定子的作用产生交流电，转子的作用是形成旋转磁场。
(7)峰峰值
峰峰值是指一个周期内信号最高值和最低值之间差的值，就是最大和最小之间的范围。它描述了信号值的变化范围的大小。
电机是驱动生产过程中各种机械最常见的设备，在工业生产、交通运输、基础建设、农业发展以及日常的普通生活中都得到了大量的使用，电机用电量在总生产用电量占比80％以上。作为一种为多行业提供动力的电气设备，其本身存在着许多潜在的故障因素，由于故障导致的停机停产会带来很大的经济损失。如果可以及时的发现电机的故障情况，在电机发生故障的早期阶段就进行检修及维护，那么就可以有效的延长电机的使用寿命并且提高整个生产体系的可靠性与稳定性。
为了保证电机的稳定运行，通过设定各类传感器来监视电机各种参数数值，如果某些参数值超过了继电器的设定值，那么继电器就会发出警报，必要时将通过电机的切断控制回路直接停止电机的运行，以防止生产事故规模的进一步扩大。
从表面上来看的话，电机的保护设置看似十分完善，但实际运行过程中继电器只有在电机故障发生时才会发出警报，然而，电机如果突然断电或者停止运行都将造成十分巨大的损失。
如图6所示，这种方式只能用于检测A点，即功能故障发生点之后的故障，在到达A点时设备完全失效。而不能找到P点、F点以及A点，即劣化起始点、潜在故障发生点以及功能故障点之间的部分，需要说明的是，电机存在潜在故障时并不是指电机已经发生了故障，是发生故障前显露出来的一种劣化现象。因此，亟需一种能够确定电机存在的潜在故障程度的方法，该潜在故障程度可以表征出电机的劣化程度。
接下来结合电机故障检测的应用场景，介绍一个本申请实施例的应用架构示意，参照图7，图7为以工业场景为例的架构示意，其中，可以在电机电控柜侧安装定子电流信号采集器，进行数据采集和上报；然后，边缘侧(边缘侧为可选的，例如，边缘侧可以为边缘网关)进行数据的汇聚和上报；中心侧(例如，服务器)可以根据上报的数据执行本申请实施例中的故障检测方法，并输出故障检测结果。
参照图8，图8为本申请实施例提供的一种故障检测方法的实施例的流程示意，其中，故障检测方法包括：
801、获取第一电流，所述第一电流为电机的定子电流。
在一种可能的实现中，为了检测电机的故障，可以对电机运行时的相关运行参数进行分析，电机的运行参数中，定子电流是电机内部相对敏感的状态参数，且作为一种非侵入式传感信号容易获取，可以在配电柜直接采集。本申请实施例中，可以通过对定子电流的谐波成分进行分析，来对电机的故障程度进行确定。
在一种可能的实现中，可以设置用于采集电机上定子电流的传感器，例如，定子电流信号采集器，传感器可以采集到电机上定子的定子电流。例如，可以在电机的电控柜侧安装定子电流信号采集器。
其中，电机定子的定子电流可以为三相电，定子电流可以为三相电中一相或多相的电流。例如三相电可以包括第一相电流、第二相电流和第三相电流，分别对应于三相电中的U相、V相以及W相。
其中，传感器可以按照一定的频率采集定子电流，为了保证后续的故障分析精度，采样频率可以示例性的至少为1K。
在一些情况下，三相电中的一相或多相电可能会存在电流值部分或者异常的情况(存在明显的数值跳变等不正常状态)，为了提高所采集的定子电流的准确性，针对于某一相电流的缺失部分或者异常部分，可以使用其他一相或者两相的相应电流值进行补全(由于三相电中不同相的电流在正常情况下仅仅是相位不同，幅值是相同的)。例如，如果采集了多相电流，可以利用电流间的相关性来进行信号预处理。例如，可以采用三相电中的多相(例如两相或者三相)中对齐相位的幅值进行融合来作为第一电流。
示例性的，融合可以为不同相的幅值相互之间的拼接，或者是求均值。
例如，可以将三相电流进行相位对齐，对齐后，进行加权平均。即current＝\sum c_{1-3}w_i*c_i/\sum c_{1-3}w_i。其中，current可以为第一电流，c_{1-3}代表各相电流，\sum_表示求和，w_i代表权重，如果判断是非异常值，权值为1，如果是异常值，权值为0。此外，还可以对采集的电流的原始信号进行其他预处理，例如，针对于缺失的数据，可以选择数据集中出现次数最多的值来填充相应的缺失数据。针对于重复数据处理，可以提取首个数据，视为新类；分析下一条数据，比较其和已存在的类的属性，当电流、电压差值小于指定阈值，分配至其相匹配的类中，并重新计算这个类的属性。如果与当前已存在的所有的类都不匹配，创建一个新的类，并创建新属性；重复前述两个步骤，直到每条记录都被扫描计算过，正确的放置到所对应的类中。
针对于异常数据，可以给定一个正常范围带，若电压电流数据不在该带内，则视为异常数据，直接剔除。
此外，由于内部噪声的干扰，采集的原始信号可能存在噪声，可以对原始信号进行去噪处理。例如，可采用小波阈值去噪方法，首先对原始信号进行小波分解，选取合适的小波系数阈值，将阈值与每个分解尺度下的高频小波系数进行比较，若小波系数大于阈值，则保留该小波系数，否则采取适当的阈值处理。将阈值处理后的小波系数进行小波逆变换，得到去噪后的重构信号。
在一种可能的实现中，第一时间段可以为连续的时间段或者是连续的时间段内的多个时刻，第一时间段也可以为不连续的时间段或者是不连续的时间段内的多个时刻，这里并不限定。例如，第一电流可以为一个时间段内多个时刻中每个时刻的电流瞬时值。
802、根据所述第一电流，得到所述第一电流的第一特征数据，所述第一特征数据与所述电机的故障有关；所述第一特征数据为所述第一电流的多个第一谐波幅值与多个第一幅值之间的数值关系，所述多个第一幅值包括所述第一电流的第一基波幅值以及多个第二谐波幅值，所述多个第二谐波幅值与所述电机的故障无关；
803、根据所述第一特征数据，确定所述电机的故障程度。
在电机出现潜在故障时，会引起电机磁场的气息的不均匀，上述现象会直接表现在定子电流上，例如：电流中会出现明显谐波成分或者是相位值的波动出现不稳定的情况，本申请中提取电机的潜在故障所引起的信号(定子电流)中的特征数据，该特征数据为定子电流中的异常成分的体现，可以基于该特征数据来确定电机存在潜在故障的程度。
电机的潜在故障所引起的信号(定子电流)中的异常成分可以为谐波成分或者是相位值的波动(变化特征)，接下来分别进行介绍：
1、特征数据为定子电流中的谐波成分。
谐波成分也就可以称之为谐波电流，谐波电流是将非正弦周期性电流函数按傅立叶级数展开时，其频率为原周期电流频率整数倍的各正弦分量的统称。
在一种可能的实现中，可以对第一电流进行傅里叶分解，得到第一电流的基波和多个谐波，电机的潜在故障可以体现在多个谐波中的一个或多个谐波上，也就是说，多个谐波中的一个或多个谐波与电机存在的潜在故障有关，电机存在的潜在故障的程度可以直接反应在多个谐波中的一个或多个谐波上。
由于并不是所有的谐波都和电机存在的潜在故障有关，有一些谐波是电机正常运行时也会存在的(例如由于电机运行的工况所导致的)，为了分析出电机存在的潜在故障的程度，可以识别出多个谐波中哪些谐波是和电机存在的潜在故障有关的。
在对第一电流进行傅里叶分解后，电机上不同结构的位置存在潜在故障相关的谐波的频率可能是不同的，例如，电机的轴承存在潜在故障可能会导致60hz处的谐波的幅值的增大。因此，可以对电机的各个结构对应的谐波频率的谐波的幅值进行分析(可选的，也可以是对全部的谐波的幅值进行分析)，若幅值满足预设条件(例如数值大于阈值或者是其他条件)，则可以认为是电机的潜在故障相关的谐波的幅值。
然而，由于受到电机运行环境等因素，可能会存在一些谐波幅值满足上述预设条件，但却不是由于电机的潜在故障所导致的，而是由电机运行环境所导致的，进而引起误判。为了解决这个问题，本申请实施例中，采用谐波乘积谱，能够准确的提取出非噪声的谐波成分。其原理是，噪声一般情况下只会引起单次谐波，而故障除了引起故障频率点的谐波外，在故障频率倍频位置也会引起谐波成分，通过融合(例如乘积，也就是式(1)所描述的)，可以将和电机潜在故障相关的谐波特征进行放大，且将噪声进行去除。
k＝1     (1)
示例性的，谐波乘积谱的原理可以如图9所示，60Hz和110Hz为和潜在故障相关的谐波的频率。
也就是说，对第一电流进行处理后，可以得到第一电流的特征数据，特征数据包括第一电流的基波的幅值(例如本申请实施例中的第一基波幅值)和多个谐波的幅值(例如本申请实施例中的多个第一谐波幅值)，其中，所述多个第一谐波幅值中的多个第一谐波幅值是和电机存在的潜在故障有关的谐波的幅值，且所述多个第一谐波幅值中的每个第一谐波幅值与对应的多个第四谐波幅值的融合结果(例如，融合结果可以是通过乘积运算、神经网络等方式得到的)满足预设条件，或者是所述多个第一谐波幅值中的每个第一谐波幅值以及对应的多个第四谐波幅值中的每个第四谐波幅值均满足预设条件，每个所述第四谐波幅值为所述第一谐波幅值对应的谐波频率的一个倍频的谐波的幅值，预设条件可以是数值大于阈值。通过上述方式，可以去除由于电机运行环境等因素所导致的误判，进而准确识别出和电机的潜在故障相关的谐波。
其中，所述多个第一谐波幅值中的每个第一谐波幅值与对应的多个第四谐波幅值的融合结果(例如，融合结果可以是通过乘积运算、神经网络等方式得到的)满足预设条件，每个所述第四谐波幅值为所述第一谐波幅值对应的谐波频率的一个倍频的谐波的幅值。通过上述方式，可以去除由于电机运行环境等因素所导致的误判，进而准确识别出和电机的潜在故障相关的谐波。
此外，电机上不同结构的位置存在潜在故障相关的谐波的频率是不同的，且存在对应关系(电机的结构和谐波频率)，不同电机具备不同的电机结构，结构和谐波频率的对应关系也可能不同，现有技术中，针对于不同的电机，可以将该电机的结构和谐波频率之间的对应关系作为先验信息，通过分析谐波频率是否异常来确定电机的哪些结构出现异常，而不属于该对应关系中电机结构对应的频率即使数值大于一定的阈值，也认为其不是故障部件对应的谐波频率。也就是说现在技术在进行故障检测时依赖先验信息。本申请实施例中，由于不需要定位出电机的哪些部件存在故障，仅仅需要确定出哪些频率的谐波是和故障相关的，通过上述倍频谐波的数值判断方法，则可以在不依赖于先验信息的情况下，准确判断出哪些部件存在故障。
上述方式仅仅能够识别出和电机潜在故障相关的谐波，以及定位出电机的哪些结构存在潜在故障，而为了能够量化出电机存在潜在故障的程度，可以对和潜在故障相关的谐波幅值进行分析。
在一种可能的实现中，所述特征数据可以包括多个第一幅值，所述多个第一幅值包括所述第一电流的第一基波幅值以及多个第二谐波幅值(可选的，所述多个第一幅值还可以包括多个第一谐波幅值)，第二谐波幅值可以是和电机运行的工况等噪声相关，而不是由电机的故障所导致产生的，所述多个第一谐波幅值中的多个第一谐波幅值与所述电机的潜在故障有关。
其中，上述与所述电机的潜在故障有关的多个第一谐波幅值的融合结果(例如本申请实施例中的第一融合结果)可以表示电机的潜在故障相关的能量，而多个幅值的融合结果(例如本申请实施例中的第二融合结果)可以表示总能量，而所述多个第一谐波幅值与所述多个第一幅值之间的数值关系，也就是电机的潜在故障相关的能量和总能量之间的数值关系，则可以表征出所述电机存在的潜在故障程度。
针对于不同电机、或者同一个电机在不同的工况等运行环境下，由于工况等噪声导致的定子电流中 的和故障相关的谐波分量可能会不同，也就是说，即使电机的故障程度相同，不同电机或者不同的工况下，和故障相关的谐波的大小也可能不同。为了消除不同工况或者电机的不同对于谐波电流大小的影响，本申请中，将和故障相关的谐波电流的幅值和对定子电流分解得到的基波以及和故障无关的谐波之间的数值关系作为特征表示来进行故障程度的确定，可以消除不同工况或者电机的不同对于谐波电流大小的影响而确定出准确的故障程度。
在一种可能的实现中，上述数值关系可以为第一融合结果和第二融合结果之间的第一差异程度。例如，所述第一融合结果或所述第二融合结果为通过累加得到的；所述第一差异程度可以为比值。
在一种可能的实现中，不同的电机、或者相同电机在不同的运行环境中，基波或者谐波的幅值都可能是不同的，仅仅利用电机在某个时间段内的特征数据并不能准确的描述出电机的潜在故障程度。例如，电机A和电机B，电机A所处的运行环境中的噪声较大，因此，即使谐波中和潜在故障相关的谐波的幅值较大(也就是潜在故障的程度较高)，在潜在故障程度较大时，也可能由于潜在故障相关的谐波的幅值和总能量之间的差异较大，而得到潜在故障程度较小的错误结论。
本申请中，为了能够适配于不同的电机、或者不同的电机运行环境，可以将电机在正常运行或者是历史运行时间段内的特征数据作为基准，利用电机实时的特征数据和基准之间的比较，来确定电机的潜在故障程度，进而可以降低不同的电机、或者相同电机在不同的运行环境的差异的干扰。
在一种可能的实现中，所述多个第一谐波幅值为多个第一频率的谐波的幅值；可以根据第一数值关系和第二数值关系之间的第二差异程度，确定所述电机存在的潜在故障程度。所述第一数值关系为所述多个第一谐波幅值与所述多个第一幅值之间的数值关系，所述第二数值关系为第二电流的多个第三谐波幅值与多个第二幅值之间的数值关系；其中，所述多个第二幅值包括所述第二电流的基波幅值以及多个谐波幅值；所述第二电流为所述电机在未发生故障的定子电流、或者在第二时间段内的定子电流；所述多个第三谐波幅值为所述多个谐波幅值中所述多个第一频率的谐波的幅值；所述第二时间段为所述第一时间段之前的时间段。
示例性的，可以计算谐波乘积谱中相应谐波能量，占信号总能量的比值，计算方法为：hocc＝\sum harm(i)除以\sum amp(i)；其中，\sum表示累加，harm(i)代表频谱中相应谐波的幅值，amp(i)代表频谱中每一个谱线的幅值。可以以初始时刻n段数据的hocc均值作为基准，计算谐波占有率的差值，作为“距离”：dis_hocc＝hocc–hocc_base。
可选的，参照图10，可以取n段正常定子电流信号(或者历史定子电流信号)间的距离进行正态分布拟合，计算均值和标准差，计算dis_hocc在正常信号分布的哪个区间，以此判定故障严重程度。如在1sigma区间外，为轻微故障；在2sigma区间外，为中度故障；在3sigma区间外为严重故障。
2、特征数据为定子电流的相位值在时域上的变化特征。
在一种可能的实现中，所述特征数据包括所述第一电流对应的第一相位值在时域上的第一变化特征；所述相位值为将所述第一电流分解得到的复数信号中的相位。可选的，所述第一变化特征可以与所述第一相位值在时域上的变化幅度有关，例如，该变化幅度可以通过峰峰值的均值表示。
当电机驱动系统出现潜在故障时，会引起电机磁场的气息的不均匀，上述现象会直接表现在定子电流上，即定子电流中的平稳成分会出现相位变化(例如可以为相位的峰峰值出现波动)。
为了提取定子电流中的平稳成分，可以基于信号预处理方法，将定子电流信号中的平稳分量分离，再进行特征的计算和提取，具体步骤可以示例性的如下：首先进行信号筛选，对信号进行短时傅里叶变换，观察主频成分波动是否超过一定阈值(例如5％)，如若未超过，则进行下一步；信号分解：对信号进行经验模态分解(empirical mode decomposition，EMD)或者集合经验模态分解(ensemble empirical mode decomposition，EEMD)，并提取其中的平稳成分，例如可以为第一个本征模态函数(intrinsic mode function，IMF)分量，具体可以参照图11所示。
对上述提取的平稳成分进行处理，得到第一电流的每个时刻的瞬时相位，再求取该段信号(也就是第一电流)瞬时相位的变化幅度。
在一种可能的实现中，所述根据所述第一变化特征，确定所述电机发生故障的故障程度，包括：根据所述第一变化特征和第二变化特征之间的差异程度，确定所述电机发生故障的故障程度；所述第二变 化特征为第二电流的多个第三谐波幅值与多个第二幅值之间的数值关系；其中，所述多个第二幅值包括所述第二电流对应的第一相位值在时域上的第二变化特征；所述第二电流为所述电机在未发生故障的定子电流、或者在第二时间段内的定子电流；所述第二时间段为所述第一时间段之前的时间段。
示例性的，可以以初始时刻n段数据的均值(例如峰峰值的均值)作为基准，计算当前值于基准值的差值，作为“距离”，得到：dis_fi＝fi–fi_base。
在一种可能的实现中，通过上述方式可以得到的距离dis_hocc(例如上述介绍的所述第一变化特征和第二变化特征之间的差异程度、以及第一数值关系和第二数值关系之间的第二差异程度)，可以用于确定潜在故障的程度。
示例性的，可以取n段正常信号或者历史信号间的距离进行正态分布拟合，计算均值和标准差，计算dis_hocc在正常信号分布的哪个区间，以此判定故障严重程度。如在1sigma区间外，为轻微故障；在2sigma区间外，为中度故障；在3sigma区间外为严重故障。
在一种可能的实现中，所述存在的潜在故障程度可以通过潜在故障级别表示，例如严重、中等或者轻微。
在一种可能的实现中，所述存在的潜在故障程度可以通过潜在故障分数，例如0到100之间的一个数值。
在一种可能的实现中，所述存在的潜在故障程度可以通过所述电极的潜在故障程度与其他电机的潜在故障程度的对比信息表示，例如电机潜在故障程度的排名。
在得到潜在故障程度后，可以利用APP等方式将电机潜在故障程度推送给用户，例如可以为相应的运维工作人员，如图12所示。
参照图13，图13为本申请实施例提供的一种故障检测方法的流程示意，如图13所示，本申请提供的故障检测方法，包括：
1301、获取第一电流，所述第一电流为电机的定子电流；
其中，关于步骤1301的具体描述可以参照上述实施例中步骤801的描述，这里不再介绍。
1302、根据所述第一电流，得到所述第一电流的第一特征数据，所述第一特征数据包括所述第一电流对应的第一相位值在时域上的第一变化特征；所述第一相位值为将所述第一电流分解得到的复数信号中的相位；所述第一变化特征与所述第一相位值在时域上的变化幅度有关；
1303、根据所述第一特征数据，确定所述电机的故障程度。
其中，关于步骤1302和步骤1303的具体描述可以参照上述实施例中步骤802和步骤803的描述，这里不再介绍。
在一种可能的实现中，所述第一电流为电机在第一时间段内的定子电流，所述方法还包括：获取第二电流，所述第二电流为所述电机在正常运行或者第二时间段内的定子电流，所述第二时间段为所述第一时间段之前的时间段；
所述根据所述第一特征数据，确定所述电机的故障程度，包括：
根据所述第二电流，得到所述第二电流的第二特征数据，所述第二特征数据和所述第一特征数据为同类型的数据；
根据所述第一特征数据和所述第二特征数据之间的差异，确定所述电机的故障程度。
在一种可能的实现中，所述第二特征数据包括所述第二电流对应的第二相位值在时域上的第二变化特征；所述第二相位值为将所述第二电流分解得到的复数信号中的相位；所述第二变化特征与所述第二相位值在时域上的变化幅度有关。
在一种可能的实现中，所述存在的故障程度通过故障级别、故障分数或者所述电极的故障程度与其他电机的故障程度的对比信息表示。
参照图14，图14为本申请实施例提供的一种故障检测装置的结构示意，如图14所示，本申请提供的故障检测装置1400，包括：
获取模块1401，用于获取第一电流，所述第一电流为电机的定子电流；
其中，关于获取模块1401的具体描述可以参照上述实施例中步骤801的描述，这里不再介绍。
特征提取模块1402，用于根据所述第一电流，得到所述第一电流的第一特征数据，所述第一特征数据与所述电机的故障有关；所述第一特征数据为所述第一电流的多个第一谐波幅值与多个第一幅值之间的数值关系，所述多个第一幅值包括所述第一电流的第一基波幅值以及多个第二谐波幅值，所述多个第二谐波幅值与所述电机的故障无关；
其中，关于特征提取模块1402的具体描述可以参照上述实施例中步骤802的描述，这里不再介绍。
故障确定模块1403，用于根据所述第一特征数据，确定所述电机的故障程度。
其中，关于故障确定模块1403的具体描述可以参照上述实施例中步骤803的描述，这里不再介绍。
在一种可能的实现中，所述第一电流为电机在第一时间段内的定子电流，所述获取模块，还用于：
获取第二电流，所述第二电流为所述电机在正常运行或者第二时间段内的定子电流，所述第二时间段为所述第一时间段之前的时间段；
所述特征提取模块，还用于：
根据所述第二电流，得到所述第二电流的第二特征数据，所述第二特征数据和所述第一特征数据为同类型的数据；
所述故障确定模块，具体用于：
根据所述第一特征数据和所述第二特征数据之间的差异，确定所述电机的故障程度。
在一种可能的实现中，所述多个第一谐波幅值与所述多个第一幅值之间的数值关系，包括：
第一融合结果和第二融合结果之间的第一差异程度；所述第一融合结果为所述多个第一谐波幅值的融合结果；所述第二融合结果为所述多个第一幅值的融合结果。
在一种可能的实现中，所述多个第一谐波幅值为所述第一电流中多个第一频率的谐波的幅值；
所述第二特征数据为所述第二电流的多个第三谐波幅值与多个第二幅值之间的数值关系；所述多个第二幅值包括所述第二电流的基波幅值以及多个谐波幅值；所述第二电流为所述电机在未发生故障的定子电流、或者在第二时间段内的定子电流；所述多个第三谐波幅值为所述多个第二幅值中所述多个第一频率的谐波的幅值。
在一种可能的实现中，所述多个第一谐波幅值中的每个第一谐波幅值、以及对应的多个第四谐波幅值中的每个第四谐波幅值均在预设的数值范围内，每个所述第四谐波幅值为所述第一谐波幅值对应的谐波频率的一个倍频的谐波的幅值；或者，
所述多个第一谐波幅值与对应的多个第四谐波幅值的融合结果在预设的数值范围内。
在一种可能的实现中，所述存在的故障程度通过故障级别、故障分数或者所述电极的故障程度与其他电机的故障程度的对比信息表示。
参照图15，图15为本申请实施例提供的一种故障检测装置的结构示意，如图15所示，本申请提供的故障检测装置1500，包括：
获取模块1501，用于获取第一电流，所述第一电流为电机的定子电流；
其中，关于故障确定模块1501的具体描述可以参照上述实施例中步骤1301的描述，这里不再介绍。
特征提取模块1502，用于根据所述第一电流，得到所述第一电流的第一特征数据，所述第一特征数据包括所述第一电流对应的第一相位值在时域上的第一变化特征；所述第一相位值为将所述第一电流分解得到的复数信号中的相位；所述第一变化特征与所述第一相位值在时域上的变化幅度有关；
其中，关于故障确定模块1502的具体描述可以参照上述实施例中步骤1302的描述，这里不再介绍。
故障确定模块1503，用于根据所述第一特征数据，确定所述电机的故障程度。
其中，关于故障确定模块1503的具体描述可以参照上述实施例中步骤1303的描述，这里不再介绍。
在一种可能的实现中，所述第一电流为电机在第一时间段内的定子电流，所述获取模块，还用于：
获取第二电流，所述第二电流为所述电机在正常运行或者第二时间段内的定子电流，所述第二时间段为所述第一时间段之前的时间段；
所述特征提取模块，还用于：
根据所述第二电流，得到所述第二电流的第二特征数据，所述第二特征数据和所述第一特征数据为 同类型的数据；
所述故障确定模块，具体用于：
根据所述第一特征数据和所述第二特征数据之间的差异，确定所述电机的故障程度。
在一种可能的实现中，所述第二特征数据包括所述第二电流对应的第二相位值在时域上的第二变化特征；所述第二相位值为将所述第二电流分解得到的复数信号中的相位；所述第二变化特征与所述第二相位值在时域上的变化幅度有关。
在一种可能的实现中，所述存在的故障程度通过故障级别、故障分数或者所述电极的故障程度与其他电机的故障程度的对比信息表示。
接下来介绍本申请实施例提供的一种故障检测装置，请参阅图16，图16为本申请实施例提供的执行设备的一种结构示意图。具体的，执行设备1600包括：接收器1601、发射器1602、处理器1603和存储器1604(其中执行设备1600中的处理器1603的数量可以一个或多个，图16中以一个处理器为例)，其中，处理器1603可以包括应用处理器16031和通信处理器16032。在本申请的一些实施例中，接收器1601、发射器1602、处理器1603和存储器1604可通过总线或其它方式连接。
存储器1604可以包括只读存储器和随机存取存储器，并向处理器1603提供指令和数据。存储器1604的一部分还可以包括非易失性随机存取存储器(non-volatile random access memory，NVRAM)。存储器1604存储有处理器和操作指令、可执行模块或者数据结构，或者它们的子集，或者它们的扩展集，其中，操作指令可包括各种操作指令，用于实现各种操作。
上述本申请实施例揭示的方法可以应用于处理器1603中，或者由处理器1603实现。处理器1603可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤可以通过处理器1603中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器1603可以是通用处理器、数字信号处理器(digital signal processing，DSP)、微处理器或微控制器，还可进一步包括专用集成电路(application specific integrated circuit，ASIC)、现场可编程门阵列(field-programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。该处理器1603可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器1604，处理器1603读取存储器1604中的信息，结合其硬件完成上述实施例提供的故障检测方法的步骤。
接收器1601可用于接收输入的数字或字符信息，以及产生与雷达系统的相关设置以及功能控制有关的信号输入。发射器1602可用于通过第一接口输出数字或字符信息；发射器1602还可用于通过第一接口向磁盘组发送指令，以修改磁盘组中的数据。
本申请实施例还提供了一种服务器，请参阅图17，图17是本申请实施例提供的服务器的一种结构示意图，服务器可因配置或性能不同而产生比较大的差异，可以包括一个或一个以上中央处理器(central processing units，CPU)1717(例如，一个或一个以上处理器)和存储器1732，一个或一个以上存储应用程序1742或数据1744的存储介质1730(例如一个或一个以上海量存储设备)。其中，存储器1732和存储介质1730可以是短暂存储或持久存储。存储在存储介质1730的程序可以包括一个或一个以上模块(图示没标出)，每个模块可以包括对训练设备中的一系列指令操作。更进一步地，中央处理器1717可以设置为与存储介质1730通信，在服务器1700上执行存储介质1730中的一系列指令操作。
服务器1700还可以包括一个或一个以上电源1726，一个或一个以上有线或无线网络接口1750，一个或一个以上输入输出接口1758，和/或，一个或一个以上操作系统1741，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM等等。
本申请实施例中，中央处理器1717，用于执行上述实施例中描述的数据处理方法。
本申请实施例中还提供一种包括计算机程序产品，当其在计算机上运行时，使得计算机执行上述实 施例中描述的故障检测方法。
本申请实施例中还提供一种计算机可读存储介质，该计算机可读存储介质中存储有用于进行信号处理的程序，当其在计算机上运行时，使得计算机执行如上述实施例中描述的故障检测方法。
本申请实施例提供的故障检测装置具体可以为芯片，芯片包括：处理单元和通信单元，该处理单元例如可以是处理器，该通信单元例如可以是输入/输出接口、管脚或电路等。该处理单元可执行存储单元存储的计算机执行指令，以使执行设备内的芯片执行上述实施例描述的图像增强方法，或者，以使训练设备内的芯片执行上述实施例描述的图像增强方法。可选地，该存储单元为该芯片内的存储单元，如寄存器、缓存等，该存储单元还可以是该无线接入设备端内的位于该芯片外部的存储单元，如只读存储器(read-only memory，ROM)或可存储静态信息和指令的其他类型的静态存储设备，随机存取存储器(random access memory，RAM)等。
具体的，请参阅图18，图18为本申请实施例提供的芯片的一种结构示意图，该芯片可以表现为神经网络处理器NPU180，NPU 180作为协处理器挂载到主CPU(Host CPU)上，由Host CPU分配任务。NPU的核心部分为运算电路1803，通过控制器1804控制运算电路1803提取存储器中的矩阵数据并进行乘法运算。
在一些实现中，运算电路1803内部包括多个处理单元(Process Engine,PE)。在一些实现中，运算电路1803是二维脉动阵列。运算电路1803还可以是一维脉动阵列或者能够执行例如乘法和加法这样的数学运算的其它电子线路。在一些实现中，运算电路1803是通用的矩阵处理器。
举例来说，假设有输入矩阵A，权重矩阵B，输出矩阵C。运算电路从权重存储器1802中取矩阵B相应的数据，并缓存在运算电路中每一个PE上。运算电路从输入存储器1801中取矩阵A数据与矩阵B进行矩阵运算，得到的矩阵的部分结果或最终结果，保存在累加器(accumulator)1808中。
统一存储器1806用于存放输入数据以及输出数据。权重数据直接通过存储单元访问控制器(direct memory access controller，DMAC)1805，DMAC被搬运到权重存储器1802中。输入数据也通过DMAC被搬运到统一存储器1806中。
BIU为Bus Interface Unit即，总线接口单元1810，用于AXI总线与DMAC和取指存储器(Instruction Fetch Buffer，IFB)1809的交互。
总线接口单元1810(Bus Interface Unit，简称BIU)，用于取指存储器1809从外部存储器获取指令，还用于存储单元访问控制器1805从外部存储器获取输入矩阵A或者权重矩阵B的原数据。
DMAC主要用于将外部存储器DDR中的输入数据搬运到统一存储器1806或将权重数据搬运到权重存储器1802中或将输入数据数据搬运到输入存储器1801中。
向量计算单元1807包括多个运算处理单元，在需要的情况下，对运算电路的输出做进一步处理，如向量乘，向量加，指数运算，对数运算，大小比较等等。主要用于神经网络中非卷积/全连接层网络计算，如Batch Normalization(批归一化)，像素级求和，对特征平面进行上采样等。
在一些实现中，向量计算单元1807能将经处理的输出的向量存储到统一存储器1806。例如，向量计算单元1807可以将线性函数和/或非线性函数应用到运算电路1803的输出，例如对卷积层提取的特征平面进行线性插值，再例如累加值的向量，用以生成激活值。在一些实现中，向量计算单元1807生成归一化的值、像素级求和的值，或二者均有。在一些实现中，处理过的输出的向量能够用作到运算电路1803的激活输入，例如用于在神经网络中的后续层中的使用。
控制器1804连接的取指存储器(instruction fetch buffer)1809，用于存储控制器1804使用的指令；
统一存储器1806，输入存储器1801，权重存储器1802以及取指存储器1809均为On-Chip存储器。外部存储器私有于该NPU硬件架构。
其中，上述任一处提到的处理器，可以是一个通用中央处理器，微处理器，ASIC，或一个或多个用于控制上述实施例中描述的故障检测方法相关步骤的程序执行的集成电路。
另外需说明的是，以上所描述的装置实施例仅仅是示意性的，其中该作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一 个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。另外，本申请提供的装置实施例附图中，模块之间的连接关系表示它们之间具有通信连接，具体可以实现为一条或多条通信总线或信号线。
通过以上的实施方式的描述，所属领域的技术人员可以清楚地了解到本申请可借助软件加必需的通用硬件的方式来实现，当然也可以通过专用硬件包括专用集成电路、专用CPU、专用存储器、专用元器件等来实现。一般情况下，凡由计算机程序完成的功能都可以很容易地用相应的硬件来实现，而且，用来实现同一功能的具体硬件结构也可以是多种多样的，例如模拟电路、数字电路或专用电路等。但是，对本申请而言更多情况下软件程序实现是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在可读取的存储介质中，如计算机的软盘、U盘、移动硬盘、ROM、RAM、磁碟或者光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，训练设备，或者网络设备等)执行本申请各个实施例该的方法。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。
该计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行该计算机程序指令时，全部或部分地产生按照本申请实施例该的流程或功能。该计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。该计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一计算机可读存储介质传输，例如，该计算机指令可以从一个网站站点、计算机、训练设备或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、训练设备或数据中心进行传输。该计算机可读存储介质可以是计算机能够存储的任何可用介质或者是包含一个或多个可用介质集成的训练设备、数据中心等数据存储设备。该可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质(例如固态硬盘(Solid State Disk，SSD))等。

Claims (23)

  1. 一种故障检测方法，其特征在于，所述方法包括：
    获取第一电流，所述第一电流为电机的定子电流；
    根据所述第一电流，得到所述第一电流的第一特征数据，所述第一特征数据与所述电机的故障有关；所述第一特征数据为所述第一电流的多个第一谐波幅值与多个第一幅值之间的数值关系，所述多个第一幅值包括所述第一电流的第一基波幅值以及多个第二谐波幅值，所述多个第二谐波幅值与所述电机的故障无关；
    根据所述第一特征数据，确定所述电机的故障程度。
  2. 根据权利要求1所述的方法，其特征在于，所述第一电流为电机在第一时间段内的定子电流，所述方法还包括：
    获取第二电流，所述第二电流为所述电机在正常运行或者第二时间段内的定子电流，所述第二时间段为所述第一时间段之前的时间段；
    所述根据所述第一特征数据，确定所述电机的故障程度，包括：
    根据所述第二电流，得到所述第二电流的第二特征数据，所述第二特征数据和所述第一特征数据为通过相同方式计算得到的数据；
    根据所述第一特征数据和所述第二特征数据之间的差异，确定所述电机的故障程度。
  3. 根据权利要求1或2所述的方法，其特征在于，所述多个第一幅值还包括所述多个第一谐波幅值。
  4. 根据权利要求1至3任一所述的方法，其特征在于，所述多个第一谐波幅值与所述多个第一幅值之间的数值关系，包括：
    第一融合结果和第二融合结果之间的第一差异程度；所述第一融合结果为所述多个第一谐波幅值的融合结果；所述第二融合结果为所述多个第一幅值的融合结果。
  5. 根据权利要求1至4任一所述的方法，其特征在于，所述多个第一谐波幅值为所述第一电流中多个第一频率的谐波的幅值；
    所述第二特征数据为所述第二电流中所述多个第一频率的谐波的多个第三谐波幅值与多个第二幅值之间的数值关系；所述多个第三谐波幅值为所述第二电流中所述多个第一频率的谐波的幅值，所述多个第二幅值包括所述第二电流的基波幅值以及多个与所述电机的故障无关的谐波幅值；所述第二电流为所述电机在未发生故障的定子电流、或者在第二时间段内的定子电流。
  6. 根据权利要求1至5任一所述的方法，其特征在于，
    所述多个第一谐波幅值中的每个第一谐波幅值、以及对应的多个第四谐波幅值中的每个第四谐波幅值均在预设的数值范围内，每个所述第四谐波幅值为所述第一谐波幅值对应的谐波频率的一个倍频的谐波的幅值；或者，
    所述多个第一谐波幅值与对应的多个第四谐波幅值的融合结果在预设的数值范围内。
  7. 根据权利要求1至6任一所述的方法，其特征在于，所述存在的故障程度通过故障级别、故障分数或者所述电极的故障程度与其他电机的故障程度的对比信息表示。
  8. 一种故障检测方法，其特征在于，所述方法包括：
    获取第一电流，所述第一电流为电机的定子电流；
    根据所述第一电流，得到所述第一电流的第一特征数据，所述第一特征数据包括所述第一电流对应 的第一相位值在时域上的第一变化特征；所述第一相位值为将所述第一电流分解得到的复数信号中的相位；所述第一变化特征与所述第一相位值在时域上的变化幅度有关；
    根据所述第一特征数据，确定所述电机的故障程度。
  9. 根据权利要求8所述的方法，其特征在于，所述第一电流为电机在第一时间段内的定子电流，所述方法还包括：
    获取第二电流，所述第二电流为所述电机在正常运行或者第二时间段内的定子电流，所述第二时间段为所述第一时间段之前的时间段；
    所述根据所述第一特征数据，确定所述电机的故障程度，包括：
    根据所述第二电流，得到所述第二电流的第二特征数据，所述第二特征数据和所述第一特征数据为通过相同方式计算得到的数据；
    根据所述第一特征数据和所述第二特征数据之间的差异，确定所述电机的故障程度。
  10. 根据权利要求8或9所述的方法，其特征在于，所述第二特征数据包括所述第二电流对应的第二相位值在时域上的第二变化特征；所述第二相位值为将所述第二电流分解得到的复数信号中的相位；所述第二变化特征与所述第二相位值在时域上的变化幅度有关。
  11. 一种故障检测装置，其特征在于，所述装置包括：
    获取模块，用于获取第一电流，所述第一电流为电机的定子电流；
    特征提取模块，用于根据所述第一电流，得到所述第一电流的第一特征数据，所述第一特征数据与所述电机的故障有关；所述第一特征数据为所述第一电流的多个第一谐波幅值与多个第一幅值之间的数值关系，所述多个第一幅值包括所述第一电流的第一基波幅值以及多个第二谐波幅值，所述多个第二谐波幅值与所述电机的故障无关；
    故障确定模块，用于根据所述第一特征数据，确定所述电机的故障程度。
  12. 根据权利要求11所述的装置，其特征在于，所述第一电流为电机在第一时间段内的定子电流，所述获取模块，还用于：
    获取第二电流，所述第二电流为所述电机在正常运行或者第二时间段内的定子电流，所述第二时间段为所述第一时间段之前的时间段；
    所述特征提取模块，还用于：
    根据所述第二电流，得到所述第二电流的第二特征数据，所述第二特征数据和所述第一特征数据为通过相同方式计算得到的数据；
    所述故障确定模块，具体用于：
    根据所述第一特征数据和所述第二特征数据之间的差异，确定所述电机的故障程度。
  13. 根据权利要求11或12所述的装置，其特征在于，所述多个第一谐波幅值与所述多个第一幅值之间的数值关系，包括：
    第一融合结果和第二融合结果之间的第一差异程度；所述第一融合结果为所述多个第一谐波幅值的融合结果；所述第二融合结果为所述多个第一幅值的融合结果。
  14. 根据权利要求11至13任一所述的装置，其特征在于，所述多个第一谐波幅值为所述第一电流中多个第一频率的谐波的幅值；
    所述第二特征数据为所述第二电流中所述多个第一频率的谐波的多个第三谐波幅值与多个第二幅值之间的数值关系；所述多个第三谐波幅值为所述第二电流中所述多个第一频率的谐波的幅值，所述多个第二幅值包括所述第二电流的基波幅值以及多个与所述电机的故障无关的谐波的幅值；所述第二电流 为所述电机在未发生故障的定子电流、或者在第二时间段内的定子电流。
  15. 根据权利要求11至14任一所述的装置，其特征在于，
    所述多个第一谐波幅值中的每个第一谐波幅值、以及对应的多个第四谐波幅值中的每个第四谐波幅值均在预设的数值范围内，每个所述第四谐波幅值为所述第一谐波幅值对应的谐波频率的一个倍频的谐波的幅值；或者，
    所述多个第一谐波幅值与对应的多个第四谐波幅值的融合结果在预设的数值范围内。
  16. 根据权利要求11至15任一所述的装置，其特征在于，所述存在的故障程度通过故障级别、故障分数或者所述电极的故障程度与其他电机的故障程度的对比信息表示。
  17. 一种故障检测装置，其特征在于，所述装置包括：
    获取模块，用于获取第一电流，所述第一电流为电机的定子电流；
    特征提取模块，用于根据所述第一电流，得到所述第一电流的第一特征数据，所述第一特征数据包括所述第一电流对应的第一相位值在时域上的第一变化特征；所述第一相位值为将所述第一电流分解得到的复数信号中的相位；所述第一变化特征与所述第一相位值在时域上的变化幅度有关；
    故障确定模块，用于根据所述第一特征数据，确定所述电机的故障程度。
  18. 根据权利要求17所述的装置，其特征在于，所述第一电流为电机在第一时间段内的定子电流，所述获取模块，还用于：
    获取第二电流，所述第二电流为所述电机在正常运行或者第二时间段内的定子电流，所述第二时间段为所述第一时间段之前的时间段；
    所述特征提取模块，还用于：
    根据所述第二电流，得到所述第二电流的第二特征数据，所述第二特征数据和所述第一特征数据为通过相同方式计算得到的数据；
    所述故障确定模块，具体用于：
    根据所述第一特征数据和所述第二特征数据之间的差异，确定所述电机的故障程度。
  19. 根据权利要求17或18所述的装置，其特征在于，所述第二特征数据包括所述第二电流对应的第二相位值在时域上的第二变化特征；所述第二相位值为将所述第二电流分解得到的复数信号中的相位；所述第二变化特征与所述第二相位值在时域上的变化幅度有关。
  20. 根据权利要求17至19任一所述的装置，其特征在于，所述存在的故障程度通过故障级别、故障分数或者所述电极的故障程度与其他电机的故障程度的对比信息表示。
  21. 一种故障检测装置，其特征在于，包括：一个或多个处理器和存储器；其中，所述存储器中存储有计算机可读指令；
    所述一个或多个处理器读取所述计算机可读指令，以使所述计算机设备实现如权利要求1至10任一所述的方法。
  22. 一种计算机可读存储介质，其特征在于，包括计算机可读指令，当所述计算机可读指令在计算机设备上运行时，使得所述计算机设备执行权利要求1至10任一项所述的方法。
  23. 一种计算机程序产品，其特征在于，包括计算机可读指令，当所述计算机可读指令在计算机设备上运行时，使得所述计算机设备执行如权利要求1至10任一所述的方法。
PCT/CN2023/114145 2022-08-30 2023-08-22 一种故障检测方法以及相关装置 WO2024046166A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211048338.5 2022-08-30
CN202211048338.5A CN117665564A (zh) 2022-08-30 2022-08-30 一种故障检测方法以及相关装置

Publications (1)

Publication Number Publication Date
WO2024046166A1 true WO2024046166A1 (zh) 2024-03-07

Family

ID=90083145

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/114145 WO2024046166A1 (zh) 2022-08-30 2023-08-22 一种故障检测方法以及相关装置

Country Status (2)

Country Link
CN (1) CN117665564A (zh)
WO (1) WO2024046166A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103926533A (zh) * 2014-03-24 2014-07-16 河海大学 永磁同步电机失磁故障在线诊断方法及系统
US20160266208A1 (en) * 2015-03-09 2016-09-15 Rolls-Royce Plc Fault detection and diagnosis in an induction motor
CN113484606A (zh) * 2021-07-06 2021-10-08 东方日立(成都)电控设备有限公司 一种高压变频器电流谐波监测报警系统及方法
CN114487911A (zh) * 2022-01-28 2022-05-13 三一汽车起重机械有限公司 匝间短路故障在线检测方法、装置、电机及作业机械

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103926533A (zh) * 2014-03-24 2014-07-16 河海大学 永磁同步电机失磁故障在线诊断方法及系统
US20160266208A1 (en) * 2015-03-09 2016-09-15 Rolls-Royce Plc Fault detection and diagnosis in an induction motor
CN113484606A (zh) * 2021-07-06 2021-10-08 东方日立(成都)电控设备有限公司 一种高压变频器电流谐波监测报警系统及方法
CN114487911A (zh) * 2022-01-28 2022-05-13 三一汽车起重机械有限公司 匝间短路故障在线检测方法、装置、电机及作业机械

Also Published As

Publication number Publication date
CN117665564A (zh) 2024-03-08

Similar Documents

Publication Publication Date Title
US10834183B2 (en) Managing idle and active servers in cloud data centers
CN113726607B (zh) 一种网络探测方法、装置、电子设备及存储介质
US20180024205A1 (en) Detecting power outages using smartphone sensors
CN114095567A (zh) 数据访问请求的处理方法、装置、计算机设备及介质
US11506717B1 (en) System and method for diagnosing stator inter-turn faults in synchronous motors
CN113627547B (zh) 训练方法、电弧检测方法、装置、电子设备及存储介质
WO2024046166A1 (zh) 一种故障检测方法以及相关装置
CN113795039B (zh) 运营商网络切换方法、装置、设备和计算机可读存储介质
CN112783731B (zh) 异常设备检测方法、装置、设备和存储介质
CN114615346A (zh) 一种协议转换方法及装置
CN109074814A (zh) 一种噪声检测方法及终端设备
Oliveira et al. Accuracy analysis using the EMD and VMD for two-terminal transmission line fault location based on traveling wave theory
CN110888036B (zh) 测试项目确定方法及装置、存储介质和电子设备
US9453863B2 (en) Implementing frequency spectrum analysis using causality Hilbert Transform results of VNA-generated S-parameter model information
US11906575B2 (en) Electrical power analyzer for large and small scale devices for environmental and ecological optimization
CN114697247A (zh) 流媒体系统的故障检测方法、装置、设备和存储介质
KR101576032B1 (ko) 전동기의 고장진단 방법
CN110220727B (zh) 一种电机类设备的异常检测方法及装置
CN113419126A (zh) 性能参数记录方法、装置、变频器、空调设备及存储介质
CN109936567A (zh) 登录信息的检测方法、装置、电子设备及存储介质
CN115576852B (zh) 模糊测试用例的质量评估方法、装置、设备以及存储介质
Najib et al. Analysis of smart IoT portal based on advanced RISC machines (ARM) processor for fanless heat maintenance
CN114791996B (zh) 信息处理方法、装置、系统、电子设备及存储介质
CN117169732B (zh) 电池故障检测方法、装置、计算设备和介质
CN114791519A (zh) 设备检测结果的获取、处理方法、设备检测方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23859200

Country of ref document: EP

Kind code of ref document: A1