Motor fault diagnosis method, system and device and storage medium

Abstract

The invention discloses a motor fault diagnosis method, system and device and a storage medium, and is applied to the technical field of motors, and the method comprises the steps: detecting the three-phase voltage and leakage current of a motor; performing feature extraction based on the three-phase voltage and the leakage current of the motor to obtain a feature extraction result; analyzing the feature extraction result to obtain a fault diagnosis result of the motor; wherein the types of the fault diagnosis results comprise motor fault-free, motor main insulation abnormity, motor turn-to-turn insulation abnormity and motor bearing abnormity. By applying the scheme of the invention, motor fault diagnosis can be conveniently and effectively carried out.

Description

Technical Field

[0001] The present invention relates to the technical field of motors, and in particular, to a method, a system, a device and a storage medium for diagnosing motor faults. Background Art

[0002] Variable-frequency motors are key equipment in many fields such as industrial production, high-speed railways, ship drives, and new energy vehicles. The problem of unexpected shutdown caused by motor faults will result in a large amount of economic losses and even cause serious safety consequences. Therefore, it is particularly important to improve the operating reliability of motors. With the technological progress of power semiconductor devices, high-frequency switching operations have become possible, which has also greatly improved the performance of PWM (Pulse Width Modulation) inverters for controlling motors. However, the rapid switching of power electronic devices will result in high dv / dt values, which will significantly increase the electrical stress on the insulating material. Voltage harmonics and high dv / dt will cause an increase in dielectric losses in the stator winding and core insulation, shortening the life of the insulating material. Also, it will cause changes in the bearing oil film capacitance and resistance (bearing electrochemical corrosion and wear), thereby affecting the service life of the bearing. According to statistics, the most common fault forms in motors are stator insulation faults, bearing faults, and rotor faults. For stator insulation faults, it will lead to serious faults such as inter-turn short circuits and even insulation failure; and as an important mechanical part that bears the load and connects the external rotating part, bearing faults will cause the failure of the entire electrical and mechanical system.

[0003] Currently, stator insulation faults and bearing faults of motors are mainly detected and repaired by offline regular disassembly, which lacks real-time performance and also requires a large amount of human resources.

[0004] In summary, how to conveniently and effectively diagnose motor faults is a technical problem that needs to be solved urgently by those skilled in the art at present. Summary of the Invention

[0005] The purpose of the present invention is to provide a method, a system, a device and a storage medium for diagnosing motor faults to conveniently and effectively diagnose motor faults.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for diagnosing motor faults, including:

[0008] Detecting the three-phase voltage and leakage current of the motor;

[0009] Performing feature extraction based on the three-phase voltage and leakage current of the motor to obtain a feature extraction result;

[0010] Analyze the feature extraction result to obtain the fault diagnosis result of the motor; wherein, the types of the fault diagnosis result include: the motor has no fault, the main insulation of the motor is abnormal, the inter-turn insulation of the motor is abnormal, and the bearing of the motor is abnormal.

[0011] In one implementation, analyzing the feature extraction result to obtain the fault diagnosis result of the motor includes:

[0012] Input the feature extraction result into a trained neural network model, and obtain the fault diagnosis result of the motor through the neural network model.

[0013] In one implementation, detecting the three-phase voltage and leakage current of the motor includes:

[0014] Whenever sampling is triggered, detect the three-phase voltage and leakage current of the motor for a first duration;

[0015] Judge whether the working condition of the motor is stable within the first duration;

[0016] If so, perform the operation of extracting features based on the three-phase voltage and leakage current of the motor to obtain the feature extraction result;

[0017] If not, discard the three-phase voltage and leakage current of the motor detected for the first duration this time.

[0018] In one implementation, judging whether the working condition of the motor is stable within the first duration includes:

[0019] Judge whether the effective value of the phase voltage and the fundamental frequency of the voltage of the motor are both stable within the first duration;

[0020] If so, determine that the working condition of the motor is stable, otherwise determine that the working condition of the motor is unstable.

[0021] In one implementation, after determining that the working condition of the motor is stable, input the feature extraction result into a trained neural network model, and obtain the fault diagnosis result of the motor through the neural network model, including:

[0022] Input the feature extraction result into a trained neural network model corresponding to the current working condition, and obtain the fault diagnosis result of the motor through the neural network model corresponding to the current working condition.

[0023] In one implementation, extracting features based on the three-phase voltage and leakage current of the motor to obtain the feature extraction result includes:

[0024] Perform spectrum analysis on the leakage current of the motor to obtain the leakage current spectrum of the motor;

[0025] Take the average value of the three-phase voltage of the motor as the common-mode voltage, and perform spectrum analysis on the common-mode voltage to obtain the common-mode voltage spectrum of the motor;

[0026] Based on the leakage current spectrum of the motor, determine the resonance frequency within the first frequency range and the amplitude of the resonance point at this resonance frequency, and determine the resonance frequency within the second frequency range and the amplitude of the resonance point at this resonance frequency;

[0027] Based on the leakage current spectrum and the common-mode voltage spectrum of the motor, determine the common-mode voltage amplitude, current amplitude, and the phase difference between the voltage and current at the fundamental frequency of the common-mode voltage when the frequency is the fundamental frequency of the common-mode voltage;

[0028] Based on the determined common-mode voltage amplitude, current amplitude, and the phase difference between the voltage and current at the fundamental frequency of the common-mode voltage when the frequency is the fundamental frequency of the common-mode voltage, determine the equivalent capacitance value of the main insulation and the equivalent resistance value of the main insulation;

[0029] Take the resonance frequency within the first frequency range and the amplitude of the resonance point at this resonance frequency, the resonance frequency within the second frequency range and the amplitude of the resonance point at this resonance frequency, the equivalent capacitance value of the main insulation, and the equivalent resistance value of the main insulation as the obtained feature extraction results.

[0030] In one embodiment, it further includes:

[0031] Based on the leakage current of the motor, determine the average value of the time-domain oscillation period and the standard deviation of the time-domain oscillation period of the leakage current, and the average value of the time-domain peak-to-peak value and the standard deviation of the time-domain peak-to-peak value of the leakage current, and add them all to the feature extraction results.

[0032] In one embodiment, based on the determined common-mode voltage amplitude, current amplitude, and the phase difference between the voltage and current at the fundamental frequency of the common-mode voltage when the frequency is the fundamental frequency of the common-mode voltage, determining the equivalent capacitance value of the main insulation and the equivalent resistance value of the main insulation includes:

[0033] Based on Determine the equivalent capacitance value of the main insulation;

[0034] Based on Determine the equivalent resistance value of the main insulation;

[0035] Wherein, C eq is the equivalent capacitance value of the main insulation, R eq is the equivalent resistance value of the main insulation, Z is the equivalent impedance of the main insulation, and , Uc, Ic, and θc are respectively the common-mode voltage amplitude, current amplitude, and phase difference between the voltage and current corresponding to the fundamental frequency of the common-mode voltage, f c is the fundamental frequency of the common-mode voltage.

[0036] In a second aspect, the present invention provides a motor fault diagnosis system, including:

[0037] A sampling module for detecting the three-phase voltage and leakage current of the motor;

[0038] A feature extraction module for extracting features based on the three-phase voltage and leakage current of the motor to obtain a feature extraction result;

[0039] A fault diagnosis module for analyzing the feature extraction result to obtain a fault diagnosis result of the motor; wherein, the types of the fault diagnosis result include: no fault in the motor, abnormal main insulation of the motor, abnormal inter-turn insulation of the motor, and abnormal bearing of the motor.

[0040] In one embodiment, the fault diagnosis module is specifically configured to:

[0041] Input the feature extraction result into a trained neural network model, and obtain the fault diagnosis result of the motor through the neural network model.

[0042] In one embodiment, the sampling module includes:

[0043] A sampling unit for detecting the three-phase voltage and leakage current of the motor for a first duration whenever sampling is triggered;

[0044] A working condition judgment unit for judging whether the working condition of the motor is stable within the first duration;

[0045] If so, trigger the feature extraction module;

[0046] If not, trigger a discard unit, and the discard unit is used to discard the three-phase voltage and leakage current of the motor detected for the first duration this time.

[0047] In one embodiment, the feature extraction module includes:

[0048] A leakage current spectrum analysis unit for performing spectrum analysis on the leakage current of the motor to obtain the leakage current spectrum of the motor;

[0049] A common-mode voltage spectrum analysis unit for taking the average value of the three-phase voltage of the motor as the common-mode voltage and performing spectrum analysis on the common-mode voltage to obtain the common-mode voltage spectrum of the motor;

[0050] A resonance point analysis unit, configured to determine the resonance frequency within a first frequency range and the resonance point amplitude at this resonance frequency based on the leakage current spectrum of the motor, and determine the resonance frequency within a second frequency range and the resonance point amplitude at this resonance frequency;

[0051] A main insulation impedance analysis unit, configured to determine the common mode voltage amplitude, current amplitude, and the phase difference between the voltage and current at the fundamental frequency of the common mode voltage when the frequency is the fundamental frequency of the common mode voltage based on the leakage current spectrum and the common mode voltage spectrum of the motor; determine the main insulation equivalent capacitance value and the main insulation equivalent resistance value based on the determined common mode voltage amplitude, current amplitude, and the phase difference between the voltage and current at the fundamental frequency of the common mode voltage when the frequency is the fundamental frequency of the common mode voltage;

[0052] A feature extraction result determination unit, configured to use the resonance frequency within the first frequency range and the resonance point amplitude at this resonance frequency, the resonance frequency within the second frequency range and the resonance point amplitude at this resonance frequency, the main insulation equivalent capacitance value, and the main insulation equivalent resistance value as the obtained feature extraction result.

[0053] In one implementation, it further includes a time-domain analysis unit, configured to:

[0054] Determine the mean value and standard deviation of the time-domain oscillation period of the leakage current, and the mean value and standard deviation of the time-domain peak-to-peak value of the leakage current based on the leakage current of the motor, and add them all to the feature extraction result.

[0055] In a third aspect, the present invention provides a motor fault diagnosis device, including:

[0056] A memory, configured to store a computer program;

[0057] A processor, configured to execute the computer program to implement the steps of the motor fault diagnosis method as described above.

[0058] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the motor fault diagnosis method as described above.

[0059] Applying the technical solution provided by the embodiments of the present invention, considering that the distributed parameters and high-frequency characteristics of the motor system result in a complex impedance network in the system, and the high-speed switching excitation of power electronics generates a large number of high-frequency multimodal switching oscillations on the distributed parameters of the motor system, which provides the feasibility for diagnosing the insulation and bearing health status of the motor by using the high-frequency switching oscillation signals generated by the self-excitation of the motor current. Specifically, by detecting the three-phase voltage and leakage current of the motor, especially the leakage current, the insulation and bearing deterioration problems of the motor can be effectively reflected. And for the convenience of analysis, feature extraction is performed based on the three-phase voltage and leakage current of the motor to obtain a feature extraction result, and then the feature extraction result is analyzed to effectively obtain the fault diagnosis result of the motor. In order to achieve a more accurate classification, the types of the fault diagnosis result need to include: no fault in the motor, abnormal main insulation of the motor, abnormal inter-turn insulation of the motor, and abnormal bearing of the motor, that is, through the solution of the present application, the classification of the main insulation / inter-turn insulation and bearing abnormalities of the motor can be effectively realized. To sum up, the solution of the present application can conveniently and effectively perform motor fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0061] Figure 1 It is a flowchart of the implementation of the motor fault diagnosis method provided by a specific embodiment of the present invention;

[0062] Figure 2 It is a schematic diagram of the equivalent circuit of the motor in a specific embodiment of the present invention;

[0063] Figure 3 It is a schematic diagram of the motor fault diagnosis principle in a specific embodiment of the present invention;

[0064] Figure 4 It is a time-domain waveform diagram of the leakage current of the motor detected in a specific embodiment of the present invention;

[0065] Figure 5 It is a single leakage current waveform in the time-domain waveform diagram of the leakage current of the motor detected in a specific embodiment of the present invention;

[0066] Figure 6 It is a schematic diagram of the leakage current spectrum of the motor obtained in a specific embodiment of the present invention;

[0067] Figure 7Schematic diagram of the leakage current spectrum and phase voltage spectrum of the motor in a specific embodiment of the present invention;

[0068] Figure 8 Schematic diagram of the structure of the motor fault diagnosis system provided by a specific embodiment of the present invention;

[0069] Figure 9 Schematic diagram of the structure of the motor fault diagnosis device provided by a specific embodiment of the present invention;

[0070] Figure 10 Schematic diagram of the structure of a computer-readable storage medium of the present invention. Specific embodiments

[0071] The core of the present invention is to provide a motor fault diagnosis method, system, device and storage medium, which can conveniently and effectively diagnose motor faults.

[0072] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0073] Please refer to Figure 1 , Figure 1 is the implementation flowchart of the motor fault diagnosis method provided by a specific embodiment of the present invention. The motor fault diagnosis method may include the following steps:

[0074] Step S101: Detect the three-phase voltage and leakage current of the motor.

[0075] The solution of the present application takes into account that the distributed parameters and high-frequency characteristics of the motor system result in a complex impedance network in the system. This impedance network not only includes the stator resistance and inductance of the motor, but also the distributed impedance between the equipment and the ground. Please refer to Figure 2 , which is the schematic diagram of the equivalent circuit of the motor. Figure 2 Cp in eq is the equivalent capacitance between turns of the motor coil, C B1 is the equivalent capacitance to the ground of the motor, C B2 and C B1 are the bearing oil film capacitances, R B2 and R C are the bearing oil film resistances, L C is the cable inductance, C L is the cable insulation capacitance, C SR is the parasitic capacitance between the stator winding and the motor rotor, C RFis the parasitic capacitance between the stator core and the motor rotor, I dv / dt is the bearing current. When the IGBT switch in the frequency converter switches from off to on, the bus voltage is directly applied to the motor coil, which will cause high-frequency oscillation of the current in the circuit. If the main insulation of the motor (i.e., the insulation between the winding and the ground), the inter-turn insulation (the insulation between each winding), and the bearing oil film capacitance deteriorate, it will cause changes in the component parameters in the complex impedance network, thus causing leakage current oscillation. Therefore, through the leakage current waveform, the fault diagnosis of the motor can be effectively realized. And this application takes into account that the three-phase voltage of the motor can also assist in the fault diagnosis of the motor. Therefore, in the solution of this application, the three-phase voltage and the leakage current of the motor will be detected.

[0076] Please refer to Figure 3 , which is a schematic diagram of the motor fault diagnosis principle in a specific embodiment. The three-phase voltage of the motor is detected by three phase voltage sensors respectively, and the leakage current sensor with three-phase sleeve is sleeved on the motor input terminal, so that the leakage current of the motor can be collected, and then the subsequent analysis and processing will be carried out by the motor fault diagnosis device. In addition, Figure 3 also shows the communication interface of the fault diagnosis device, indicating that the fault diagnosis result can be output based on the communication interface.

[0077] When detecting the three-phase voltage and the leakage current of the motor, it can usually be detected periodically. For example, in one case, the detection frequency can reach more than 30 MHz. In addition, the solution of this application can collect the leakage currents of the U, V, and W phases of the motor through the current sensor sleeved at the motor input terminal. Since the leakage current characteristics of the motor insulation weakening usually focus on the leakage current characteristics of dozens to hundreds of kHz, and it can be known from the test data that the detection mode sensitive to the change of the oil film capacitance is at the megahertz level. Therefore, in the solution of this application, the leakage current sensor needs to meet the sampling requirement of milliamperes, and the sensor bandwidth should satisfy no obvious signal attenuation below 30 MHz to effectively ensure the stability and accuracy of the original data, which is also conducive to ensuring the accuracy of the fault diagnosis result. In addition, the aperture of the leakage current sensor needs to reach millimeters (x here is the diameter of the large motor wire), so that the leakage current sensor can sleeve the three large wires of the motor, and the signal frequency band is 1 kHz - 30 MHz.

[0078] The phase voltage sensor can be set at the motor input terminal to collect the phase-to-ground voltages of the U, V, and W phases of the motor respectively. The range of the phase voltage sensor needs to meet the phase voltage measurement requirements corresponding to the motor model, and the signal frequency band usually needs to reach 10 Hz - 500 kHz.

[0079] In a specific embodiment of the present invention, step S101 may include:

[0080] Whenever sampling is triggered, the three-phase voltage and leakage current of the motor for the first duration are detected;

[0081] Judge whether the working condition of the motor is stable within the first duration;

[0082] If so, perform the operation of feature extraction based on the three-phase voltage and leakage current of the motor to obtain the feature extraction result;

[0083] If not, discard the three-phase voltage and leakage current of the motor for the first duration detected this time.

[0084] This implementation mode takes into account that in order to facilitate subsequent feature extraction, the three-phase voltage and leakage current can be collected for a period of time, and subsequent feature extraction can be realized based on the three-phase voltage and leakage current of this period of time. For this reason, in this implementation mode, whenever sampling is triggered, the three-phase voltage and leakage current of the motor for the first duration are detected. For example, in a certain situation, the sampling frequency reaches more than 30 MHz, and the acquisition length of each piece of data is set to 0.1 s, that is, the first duration is set to 0.1 second.

[0085] In addition, in this implementation mode, the specific timing of triggering sampling can be set and adjusted according to actual needs. For example, whenever sampling is triggered and the three-phase voltage and leakage current of the motor for the first duration are detected, after an interval of time, the next sampling can be triggered. Another example is that whenever sampling is triggered and the three-phase voltage and leakage current of the motor for the first duration are detected, the next sampling can be triggered immediately.

[0086] After the three-phase voltage and leakage current of the motor for the first duration are detected, in this implementation mode, it will be judged whether the working condition of the motor is stable within this first duration. This is because the working condition of the motor will also have a certain impact on the leakage current characteristics. In order to shield the influence of the motor working condition factor and ensure the reliability of the diagnosis result, the three-phase voltage and leakage current of the motor for the first duration detected should be detected under a stable working condition. For this reason, in this implementation mode, it will be judged whether the working condition of the motor is stable within the first duration. If the working condition is stable, the subsequent operation of step S102 can be normally executed. Correspondingly, if the working condition of the motor is not stable within this first duration, the three-phase voltage and leakage current of the motor for the first duration detected this time can be discarded to avoid incorrect fault diagnosis results.

[0087] There can be various specific ways to judge whether the working condition of the motor is stable. For example, in a specific implementation mode of the present invention, to judge whether the working condition of the motor is stable within the first duration, it can specifically include:

[0088] Judge whether the effective value of the phase voltage and the fundamental frequency of the voltage of the motor remain stable within the first duration;

[0089] If so, it is determined that the operating condition of the motor is stable; otherwise, it is determined that the operating condition of the motor is unstable.

[0090] As described above, the operating condition of the motor will have a certain degree of influence on the leakage current characteristics. Specifically, in this implementation manner, it is considered that the main influencing factors are the speed and torque of the motor. Therefore, in order to ensure the reliability of the diagnosis result, it is mainly necessary to shield the influence of the speed and torque of the motor. The torque of the motor will be reflected in the effective value of the phase voltage, and the fundamental voltage frequency is related to the speed of the motor. Therefore, in this implementation manner, it will be judged whether both the effective value of the phase voltage and the fundamental voltage frequency of the motor remain stable within the first time period. If they are stable, it indicates that within the first time period, the speed and torque of the motor are relatively stable, so the operating condition of the motor can be regarded as stable; otherwise, it can be determined that the operating condition of the motor is unstable.

[0091] There can be various specific ways to judge whether both the effective value of the phase voltage and the fundamental voltage frequency of the motor remain stable within the first time period. Taking the effective value of the phase voltage as an example, for example, the average value a of the effective value of the phase voltage of the motor within the first time period can be determined. If within the first time period, in more than b% of the time periods, the effective value of the phase voltage of the motor remains within the range of a±c, it can be regarded that within the first time period, the effective value of the phase voltage of the motor remains stable; otherwise, it is regarded as unstable. Another example is that the change range of the effective value of the phase voltage of the motor within the first time period can be determined. If this change range exceeds the set threshold, it can be regarded that within the first time period, the effective value of the phase voltage of the motor remains stable; otherwise, it is regarded as unstable. According to the same principle, it can also be judged whether the fundamental voltage frequency of the motor remains stable within the first time period.

[0092] In the above implementation manner, based on the effective value of the phase voltage and the fundamental voltage frequency of the motor, it is judged whether the operating condition of the motor is stable. In some implementation manners, considering that there are various ways to calculate the speed and torque of the motor and they are not complex, therefore, the speed and torque of the motor within the first time period can also be determined, and then by judging whether both the speed and torque of the motor remain stable within the first time period, it is determined whether the operating condition of the motor is stable.

[0093] Step S102: Extract features based on the three-phase voltage and leakage current of the motor to obtain a feature extraction result.

[0094] This application considers that if directly analyzing based on the three-phase voltage and leakage current of the motor, neither the convenience of the analysis can be guaranteed nor the accuracy of the motor fault diagnosis result is conducive to being guaranteed. Therefore, features can be extracted first based on the three-phase voltage and leakage current of the motor to obtain a feature extraction result, and then the feature extraction result is analyzed to obtain the motor fault diagnosis result.

[0095] Of course, there can be multiple specific ways of feature extraction, as long as the features that are conducive to obtaining accurate motor fault diagnosis results can be extracted.

[0096] For example, in a specific embodiment of the present invention, step S102 may include the following steps:

[0097] Step 1: Perform spectral analysis on the leakage current of the motor to obtain the leakage current spectrum of the motor; take the average value of the three-phase voltages of the motor as the common-mode voltage, and perform spectral analysis on the common-mode voltage to obtain the common-mode voltage spectrum of the motor;

[0098] Step 2: Based on the leakage current spectrum of the motor, determine the resonance frequency within the first frequency range and the amplitude of the resonance point at this resonance frequency, and determine the resonance frequency within the second frequency range and the amplitude of the resonance point at this resonance frequency;

[0099] Step 3: Based on the leakage current spectrum and the common-mode voltage spectrum of the motor, determine the common-mode voltage amplitude, current amplitude, and the phase difference between the voltage and current at the fundamental frequency of the common-mode voltage when the frequency is the fundamental frequency of the common-mode voltage;

[0100] Step 4: Based on the determined common-mode voltage amplitude, current amplitude, and the phase difference between the voltage and current at the fundamental frequency of the common-mode voltage when the frequency is the fundamental frequency of the common-mode voltage, determine the main insulation equivalent capacitance value and the main insulation equivalent resistance value;

[0101] Step 5: Take the resonance frequency within the first frequency range and the amplitude of the resonance point at this resonance frequency, the resonance frequency within the second frequency range and the amplitude of the resonance point at this resonance frequency, the main insulation equivalent capacitance value, and the main insulation equivalent resistance value as the obtained feature extraction results.

[0102] This embodiment takes into account that for the three-phase voltage and leakage current of the motor, the features in the frequency domain are helpful for analyzing more accurate motor fault diagnosis results. Therefore, spectral analysis is performed on the motor to obtain the common-mode voltage spectrum and the leakage current spectrum of the motor. In particular, the leakage current spectrum of the motor is helpful for effectively distinguishing insulation abnormalities and bearing abnormalities.

[0103] See Figure 4 , which is the time-domain waveform diagram of the leakage current of the motor detected in a specific embodiment, and Figure 5 is a single leakage current waveform in this time-domain waveform diagram. Figure 4 and Figure 5The horizontal axes all represent time, and the vertical axes are the amplitudes of the leakage current in the time domain. For example, in this implementation, whenever sampling is triggered, the three-phase voltage and leakage current of the motor for the first duration are detected. For example, the sampling frequency reaches above 30 MHz, and the first duration is set to 0.1 seconds. Then Figure 4 in it, it is the time-domain waveform diagram of the leakage current of the motor for this 0.1 second. For this 0.1-second acquisition window, it will contain multiple oscillating current waveforms. Figure 5 What is shown is a single leakage current waveform.

[0104] By performing a fast Fourier transform on Figure 4 the time-domain waveform diagram of the leakage current of this motor, the leakage current spectrum of the motor can be obtained. Refer to Figure 6 which is a schematic diagram of the leakage current spectrum of the motor obtained in a specific implementation. Figure 6 The horizontal axis represents frequency, and the vertical axis is the amplitude.

[0105] When the component parameters in the complex impedance network change, it will cause Figure 6 the resonance point frequency in it to shift, and the resonance point amplitude will also change. And due to the resonance point mode change caused by the motor insulation and the resonance point mode change caused by the oil film capacitance, there are obvious differences, specifically manifested as: the resonance point frequencies corresponding to the motor insulation deterioration are distributed in a lower frequency band, while the resonance point frequencies corresponding to the oil film capacitance will be distributed in a higher frequency band, usually reaching above MHz, so that the two characteristics will not interfere with each other.

[0106] In this regard, in this implementation, the resonance frequency within the first frequency range and the resonance point amplitude at this resonance frequency can be determined based on the leakage current spectrum of the motor. The first frequency range is a low-frequency range. For example, in Figure 6 the example, the resonance frequency within the determined first frequency range is f1, and the resonance point amplitude at this resonance frequency is denoted as A1. The second frequency range is a high-frequency range. In Figure 6 the example, the resonance frequency within the determined second frequency range is f2, and the resonance point amplitude at this resonance frequency is denoted as A2.

[0107] It can be understood from the above analysis that f1 and A1 under normal conditions of the motor will be different from f1 and A1 under the condition of motor insulation deterioration, and f2 and A2 under normal conditions of the motor will be different from f2 and A2 under the condition of bearing abnormality.

[0108] This embodiment further considers that the motor insulation deterioration includes the main insulation deterioration between the motor and the ground and the turn - to - turn insulation deterioration. The degrees of influence of the two on the overall impedance of the motor are different. The main insulation deterioration has a greater impact on the impedance between the motor and the ground. Therefore, the impedance between the motor and the ground can be further identified to distinguish the main insulation deterioration and the turn - to - turn insulation deterioration, improving the accuracy of fault diagnosis.

[0109] The impedance between the motor and the ground can be reflected by the main insulation equivalent capacitance value and the main insulation equivalent resistance value. Therefore, in this embodiment, based on the leakage current spectrum and the common - mode voltage spectrum of the motor, the common - mode voltage amplitude, the current amplitude, and the phase difference between the voltage and the current at the fundamental frequency of the common - mode voltage are determined.

[0110] The common - mode voltage spectrum needs to be determined based on the three - phase voltages. Specifically, the three - phase voltages of the motor are obtained through phase - voltage detection, and then the average value is used as the common - mode voltage. It can be expressed as:

[0111] . Here, U a , U b , U c represent the three - phase voltages, and U is the average value of the three - phase voltages. After obtaining the common - mode voltage, spectral analysis needs to be performed on the common - mode voltage, and the obtained spectrum is called the common - mode voltage spectrum of the motor.

[0112] Refer to Figure 7 . Figure 7 On the right side of Figure 7 is the leakage current spectrum of the motor, and on the left side is the common - mode voltage spectrum. For the leakage current spectrum of the motor, the current amplitude corresponding to the fundamental frequency fc of the common - mode voltage needs to be determined. Figure 7 In

[0113] this current amplitude is denoted as Ic. Correspondingly, for the common - mode voltage spectrum of the motor, the common - mode voltage amplitude corresponding to the fundamental frequency fc of the common - mode voltage needs to be determined.

[0114] In

[0115] this common - mode voltage amplitude is denoted as Uc. In addition, the phase difference between the voltage and the current at this frequency fc needs to be determined. After obtaining the common - mode voltage amplitude, the current amplitude, and the phase difference between the voltage and the current at the fundamental frequency of the common - mode voltage, the main insulation equivalent capacitance value and the main insulation equivalent resistance value can be determined accordingly.

[0114] Finally, in this embodiment, the resonance frequency f1 within the first frequency range and the resonance point amplitude A1 at this resonance frequency, the resonance frequency f2 within the second frequency range and the resonance point amplitude A2 at this resonance frequency, the main insulation equivalent capacitance value, and the main insulation equivalent resistance value can be used as the obtained feature extraction results.

[0115] Based on the common-mode voltage amplitude, current amplitude, and phase difference between voltage and current corresponding to the fundamental frequency of the common-mode voltage, the equivalent capacitance value and equivalent resistance value of the main insulation are determined. There can be various specific calculation methods. For example, in a specific embodiment of the present invention, step four may specifically include:

[0116] Based on Determine the equivalent capacitance value of the main insulation;

[0117] Based on Determine the equivalent resistance value of the main insulation;

[0118] Where C eq is the equivalent capacitance value of the main insulation, R eq is the equivalent resistance value of the main insulation, Z is the equivalent impedance of the main insulation, and , Uc, Ic, and θc are respectively the common-mode voltage amplitude, current amplitude, and phase difference between voltage and current corresponding to the fundamental frequency of the common-mode voltage, and f c is the fundamental frequency of the common-mode voltage.

[0119] In this embodiment, the equivalent capacitance value C eq and the equivalent resistance value R eq of the main insulation can be conveniently calculated.

[0120] Furthermore, in a specific embodiment of the present invention, it may further include:

[0121] Based on the leakage current of the motor, determine the average value and standard deviation of the time-domain oscillation period of the leakage current, and the average value and standard deviation of the time-domain peak-to-peak value of the leakage current, and add them all to the feature extraction result.

[0122] This embodiment considers that although the features in the frequency domain are helpful for analyzing a more accurate fault diagnosis result of the motor, some time-domain features can also help to improve the accuracy of the fault diagnosis result to a certain extent. And through experimental analysis, the applicant found that the time-domain oscillation period and peak-to-peak value of the leakage current are helpful for improving the accuracy of the fault diagnosis result of the motor.

[0123] And it can be referred to Figure 4 and Figure 5 , for Figure 4 this 0.1-second acquisition window, which will contain multiple oscillating current waveforms, Figure 5 what is shown is a single leakage current waveform, and Figure 5The time-domain oscillation period Ta and the peak-to-peak value Arange of the single leakage current waveform are shown. Therefore, in this embodiment, for the time-domain oscillation period, the mean value and the standard deviation of the time-domain oscillation period of the leakage current are calculated. Similarly, for the peak-to-peak value, the mean value and the standard deviation of the peak-to-peak value are calculated, and both are added to the feature extraction result.

[0124] Step S103: Analyze the feature extraction result to obtain the fault diagnosis result of the motor; wherein, the types of the fault diagnosis result include: the motor has no fault, the main insulation of the motor is abnormal, the inter-turn insulation of the motor is abnormal, and the bearing of the motor is abnormal.

[0125] By analyzing the feature extraction result, the fault diagnosis result of the motor can be obtained. There are various specific analysis methods that can be used. For example, f1 and A1 in the feature extraction result can be compared with f1 and A1 under normal conditions of the motor determined in advance to determine whether there is insulation abnormality, and f2 and A2 in the feature extraction result can be compared with f2 and A2 under normal conditions of the motor determined in advance to determine whether there is an abnormality in the motor bearing.

[0126] In a specific embodiment of the present invention, step S103 may specifically include:

[0127] Input the feature extraction result into a trained neural network model, and obtain the fault diagnosis result of the motor through the neural network model.

[0128] This embodiment considers that since there are usually various types of features in the feature extraction result, using a neural network can more conveniently achieve comprehensive evaluation and obtain a more accurate fault diagnosis result. A neural network model is a complex network system formed by a large number of simple processing units (neurons) widely interconnected. It has large-scale parallelism, distributed storage and processing, self-organization, self-adaptation, and self-learning capabilities, and is particularly suitable for processing problems of imprecise and fuzzy information that require considering multiple factors and conditions simultaneously. Compared with methods such as manual scoring (such as the analytic hierarchy process), a neural network model trained based on a large amount of experimental data can effectively reduce the interference caused by subjective factors and ensure the accuracy of the fault diagnosis result.

[0129] In a specific embodiment of the present invention, after determining that the working condition of the motor is stable, inputting the feature extraction result into a trained neural network model and obtaining the fault diagnosis result of the motor through the neural network model may specifically include:

[0130] Input the feature extraction result into a trained neural network model corresponding to the current working condition, and obtain the fault diagnosis result of the motor through the neural network model corresponding to the current working condition.

[0131] This embodiment takes into account that in order to further ensure the accuracy of the fault diagnosis result and eliminate the interference of the working conditions, for different working conditions of the motor, corresponding neural network models can be pre-trained. So that whenever sampling is triggered subsequently, after detecting the three-phase voltage and leakage current of the motor for the first duration and obtaining the feature extraction result of this time, the feature extraction result needs to be input into the neural network model corresponding to this working condition. As described above, in the solution of this application, the motor working condition can be measured by speed and torque, or by the effective voltage value and fundamental wave frequency. Taking speed and torque as an example, in practical applications, in order to avoid setting too many neural network models, the speed can be divided into several interval ranges. Similarly, the torque is also divided into several interval ranges. Then through combination, each working condition can be obtained, and then corresponding numbers of neural network models can be trained according to different working conditions.

[0132] Applying the technical solution provided by the embodiment of the present invention, considering that the distributed parameters and high-frequency characteristics of the motor system result in a complex impedance network in the system, and the high-speed switching excitation of power electronics generates a large number of high-frequency multimodal switching oscillations on the distributed parameters of the motor system, which provides the feasibility for diagnosing the insulation and bearing health status of the motor by using the high-frequency switching oscillation signal generated by the self-excitation of the motor current. Specifically, by detecting the three-phase voltage and leakage current of the motor, especially the leakage current, the insulation and bearing deterioration problems of the motor can be effectively reflected. And for the convenience of analysis, feature extraction is performed based on the three-phase voltage and leakage current of the motor to obtain the feature extraction result, and then the feature extraction result is analyzed to effectively obtain the fault diagnosis result of the motor. In order to achieve more accurate classification, the types of fault diagnosis results need to include: the motor has no fault, the main insulation of the motor is abnormal, the inter-turn insulation of the motor is abnormal, and the bearing of the motor is abnormal. That is, through the solution of this application, the classification of the main insulation / inter-turn insulation and bearing abnormality of the motor can be effectively realized. To sum up, the solution of this application can conveniently and effectively perform motor fault diagnosis.

[0133] Corresponding to the above method embodiment, the embodiment of the present invention also provides a motor fault diagnosis system, which can be mutually corresponding and referred to above.

[0134] See Figure 8 As shown, it is a schematic structural diagram of a motor fault diagnosis system in the present invention, including:

[0135] A sampling module 801, configured to detect the three-phase voltage and leakage current of the motor;

[0136] A feature extraction module 802, configured to perform feature extraction based on the three-phase voltage and leakage current of the motor to obtain a feature extraction result;

[0137] A fault diagnosis module 803 is configured to analyze the feature extraction result to obtain a fault diagnosis result of the motor. The types of the fault diagnosis result include: no fault in the motor, abnormal main insulation of the motor, abnormal inter-turn insulation of the motor, and abnormal bearing of the motor.

[0138] In a specific embodiment of the present invention, the fault diagnosis module is specifically configured to:

[0139] Input the feature extraction result into a trained neural network model, and obtain the fault diagnosis result of the motor through the neural network model.

[0140] In a specific embodiment of the present invention, the sampling module 801 includes:

[0141] A sampling unit is configured to detect the three-phase voltage and leakage current of the motor for a first duration whenever sampling is triggered.

[0142] A working condition judgment unit is configured to judge whether the working condition of the motor is stable within the first duration.

[0143] If so, trigger the feature extraction module 802.

[0144] If not, trigger a discard unit, and the discard unit is configured to discard the three-phase voltage and leakage current of the motor detected for the first duration this time.

[0145] In a specific embodiment of the present invention, the working condition judgment unit is specifically configured to:

[0146] Judge whether both the effective value of the phase voltage and the fundamental frequency of the voltage of the motor remain stable within the first duration.

[0147] If so, determine that the working condition of the motor is stable, otherwise determine that the working condition of the motor is unstable.

[0148] In a specific embodiment of the present invention, the fault diagnosis module 803 is specifically configured to:

[0149] Input the feature extraction result into a trained neural network model corresponding to the current working condition, and obtain the fault diagnosis result of the motor through the neural network model corresponding to the current working condition.

[0150] In a specific embodiment of the present invention, the feature extraction module 802 includes:

[0151] A leakage current spectrum analysis unit is configured to perform spectrum analysis on the leakage current of the motor to obtain the leakage current spectrum of the motor.

[0152] A common-mode voltage spectrum analysis unit is configured to use the average value of the three-phase voltage of the motor as the common-mode voltage, and perform spectrum analysis on the common-mode voltage to obtain the common-mode voltage spectrum of the motor.

[0153] A resonance point analysis unit, configured to determine the resonance frequency within a first frequency range and the resonance point amplitude at the resonance frequency based on the leakage current spectrum of the motor, and determine the resonance frequency within a second frequency range and the resonance point amplitude at the resonance frequency;

[0154] A main insulation impedance analysis unit, configured to determine the common mode voltage amplitude, current amplitude, and the phase difference between the voltage and current at the common mode voltage fundamental frequency based on the leakage current spectrum and the common mode voltage spectrum of the motor; determine the main insulation equivalent capacitance value and the main insulation equivalent resistance value based on the determined common mode voltage amplitude, current amplitude, and the phase difference between the voltage and current at the common mode voltage fundamental frequency;

[0155] A feature extraction result determination unit, configured to use the resonance frequency within the first frequency range and the resonance point amplitude at the resonance frequency, the resonance frequency within the second frequency range and the resonance point amplitude at the resonance frequency, the main insulation equivalent capacitance value, and the main insulation equivalent resistance value as the obtained feature extraction result.

[0156] In a specific embodiment of the present invention, it further includes a time domain analysis unit, configured to:

[0157] Based on the leakage current of the motor, determine the mean value and standard deviation of the time domain oscillation period of the leakage current, and the mean value and standard deviation of the time domain peak-to-peak value of the leakage current, and add them all to the feature extraction result.

[0158] In a specific embodiment of the present invention, the main insulation impedance analysis unit determines the main insulation equivalent capacitance value and the main insulation equivalent resistance value based on the determined common mode voltage amplitude, current amplitude, and the phase difference between the voltage and current at the common mode voltage fundamental frequency, including:

[0159] Based on Determine the main insulation equivalent capacitance value;

[0160] Based on Determine the main insulation equivalent resistance value;

[0161] Wherein, C eq is the main insulation equivalent capacitance value, R eq is the main insulation equivalent resistance value, Z is the main insulation equivalent impedance, and , Uc, Ic, and θc are respectively the common mode voltage amplitude, current amplitude, and the phase difference between the voltage and current at the common mode voltage fundamental frequency, and f c is the common mode voltage fundamental frequency.

[0162] Corresponding to the above method and system embodiments, an embodiment of the present invention further provides a motor fault diagnosis device and a computer-readable storage medium, which can be correspondingly referred to with the above text.

[0163] See Figure 9 As shown, the device may include:

[0164] A sensor 901 for signal sampling;

[0165] A memory 902 for storing computer programs;

[0166] A processor 903 for executing the computer program to implement the steps of the motor fault diagnosis method in any of the above embodiments.

[0167] Refer to Figure 10 , a computer program 91 is stored on the computer-readable storage medium 90, and when the computer program 91 is executed by the processor, the steps of the motor fault diagnosis method in any of the above embodiments are implemented. The computer-readable storage medium 90 mentioned here includes random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium well-known in the technical field.

[0168] It should also be noted that in this application, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0169] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this application can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention. Specific examples are applied in this application to elaborate on the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the technical solution and its core idea of the present invention. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the protection scope of the present invention.

Claims

1. A method for diagnosing motor faults, characterized in that, Including: Detecting the three-phase voltage and leakage current of the motor; Performing feature extraction based on the three-phase voltage and leakage current of the motor to obtain a feature extraction result; Analyzing the feature extraction result to obtain a fault diagnosis result of the motor; wherein, the types of the fault diagnosis result include: no fault of the motor, abnormal main insulation of the motor, abnormal inter-turn insulation of the motor, and abnormal bearing of the motor.

2. The motor fault diagnosis method according to claim 1, wherein Analyzing the feature extraction result to obtain a fault diagnosis result of the motor, including: Inputting the feature extraction result into a trained neural network model, and obtaining a fault diagnosis result of the motor through the neural network model.

3. The motor fault diagnosis method according to claim 2, wherein, Detecting the three-phase voltage and leakage current of the motor, including: Whenever sampling is triggered, detecting the three-phase voltage and leakage current of the motor for a first duration; Judging whether the operating condition of the motor is stable within the first duration; If so, performing the operation of performing feature extraction based on the three-phase voltage and leakage current of the motor to obtain a feature extraction result; If not, discarding the three-phase voltage and leakage current of the motor detected for the first duration this time.

4. The motor fault diagnosis method according to claim 3, characterized in that, Judging whether the operating condition of the motor is stable within the first duration, including: Judging whether the effective value of the phase voltage and the fundamental frequency of the voltage of the motor both remain stable within the first duration; If so, determining that the operating condition of the motor is stable, otherwise determining that the operating condition of the motor is unstable.

5. The motor fault diagnosis method according to claim 3, characterized in that After determining that the operating condition of the motor is stable, inputting the feature extraction result into a trained neural network model, and obtaining a fault diagnosis result of the motor through the neural network model, including: Inputting the feature extraction result into a trained neural network model corresponding to the current operating condition, and obtaining a fault diagnosis result of the motor through the neural network model corresponding to the current operating condition.

6. The motor fault diagnosis method according to any one of claims 1 to 5, characterized in that, Performing feature extraction based on the three-phase voltage and leakage current of the motor to obtain a feature extraction result, including: Performing spectrum analysis on the leakage current of the motor to obtain the leakage current spectrum of the motor; Taking the average value of the three-phase voltage of the motor as the common-mode voltage, and performing spectrum analysis on the common-mode voltage to obtain the common-mode voltage spectrum of the motor; Based on the leakage current spectrum of the motor, determining the resonance frequency within a first frequency range and the resonance point amplitude at the resonance frequency, and determining the resonance frequency within a second frequency range and the resonance point amplitude at the resonance frequency; Based on the leakage current spectrum and the common-mode voltage spectrum of the motor, determining the common-mode voltage amplitude, current amplitude, and the phase difference between the voltage and current at the fundamental frequency of the common-mode voltage when the frequency is the fundamental frequency of the common-mode voltage; Based on the determined common-mode voltage amplitude, current amplitude, and the phase difference between the voltage and current at the fundamental frequency of the common-mode voltage when the frequency is the fundamental frequency of the common-mode voltage, determining the main insulation equivalent capacitance value and the main insulation equivalent resistance value; Take the resonant frequency within the first frequency range and the resonant point amplitude at this resonant frequency, the resonant frequency within the second frequency range and the resonant point amplitude at this resonant frequency, the equivalent capacitance value of the main insulation and the equivalent resistance value of the main insulation as the obtained feature extraction result.

7. The motor fault diagnosis method according to claim 6, wherein It further includes: Based on the leakage current of the motor, determine the mean value of the time-domain oscillation period and the standard deviation of the time-domain oscillation period of the leakage current, as well as the mean value of the time-domain peak-to-peak value and the standard deviation of the time-domain peak-to-peak value of the leakage current, and add them all to the feature extraction result.

8. The motor fault diagnosis method according to claim 6, wherein, Based on the determined common-mode voltage amplitude, current amplitude and the phase difference between the voltage and current at the common-mode voltage fundamental frequency when the frequency is the common-mode voltage fundamental frequency, determine the equivalent capacitance value and the equivalent resistance value of the main insulation, including: Based on determine the equivalent capacitance value of the main insulation; Based on the equivalent resistance value of the main insulation is determined; Among them, C eq is the equivalent capacitance value of the main insulation, R eq is the equivalent resistance value of the main insulation, Z is the equivalent impedance of the main insulation, and , Uc, Ic, and θc are respectively the common-mode voltage amplitude, current amplitude, and phase difference between the voltage and current corresponding to the fundamental frequency of the common-mode voltage, and f c is the fundamental frequency of the common-mode voltage.

9. A motor fault diagnosis system, characterized in that, It includes: A sampling module for detecting the three-phase voltage and leakage current of the motor; A feature extraction module for performing feature extraction based on the three-phase voltage and leakage current of the motor to obtain a feature extraction result; A fault diagnosis module for analyzing the feature extraction result to obtain the fault diagnosis result of the motor; wherein, the types of the fault diagnosis result include: the motor has no fault, the main insulation of the motor is abnormal, the inter-turn insulation of the motor is abnormal, and the bearing of the motor is abnormal.

10. The motor fault diagnosis system according to claim 9, wherein The fault diagnosis module is specifically used for: Input the feature extraction result into a trained neural network model, and obtain the fault diagnosis result of the motor through the neural network model.

11. The motor fault diagnosis system according to claim 10, wherein, The sampling module includes: A sampling unit for detecting the three-phase voltage and leakage current of the motor for a first duration whenever sampling is triggered; A working condition judgment unit for judging whether the working condition of the motor is stable within the first duration; If so, trigger the feature extraction module; If not, trigger a discard unit, and the discard unit is used to discard the three-phase voltage and leakage current of the motor detected for the first duration this time.

12. The motor fault diagnosis system according to any one of claims 9 to 11, characterized in that, The feature extraction module includes: A leakage current spectrum analysis unit for performing spectrum analysis on the leakage current of the motor to obtain the leakage current spectrum of the motor; A common-mode voltage spectrum analysis unit for taking the average value of the three-phase voltage of the motor as the common-mode voltage and performing spectrum analysis on the common-mode voltage to obtain the common-mode voltage spectrum of the motor; A resonant point analysis unit for determining the resonant frequency within the first frequency range and the resonant point amplitude at this resonant frequency based on the leakage current spectrum of the motor, and determining the resonant frequency within the second frequency range and the resonant point amplitude at this resonant frequency; A main insulation impedance analysis unit for determining the common-mode voltage amplitude, current amplitude and the phase difference between the voltage and current at the common-mode voltage fundamental frequency when the frequency is the common-mode voltage fundamental frequency based on the leakage current spectrum and the common-mode voltage spectrum of the motor; based on the determined common-mode voltage amplitude, current amplitude and the phase difference between the voltage and current at the common-mode voltage fundamental frequency when the frequency is the common-mode voltage fundamental frequency, determine the equivalent capacitance value and the equivalent resistance value of the main insulation; A feature extraction result determination unit, configured to use the resonant frequencies within the first frequency range and the resonant point amplitudes at these resonant frequencies, the resonant frequencies within the second frequency range and the resonant point amplitudes at these resonant frequencies, the equivalent capacitance value of the main insulation, and the equivalent resistance value of the main insulation as the obtained feature extraction result.

13. The motor fault diagnosis system according to claim 12, characterized in that, It further includes a time-domain analysis unit, configured to: Based on the leakage current of the motor, determine the mean value and standard deviation of the time-domain oscillation period of the leakage current, and the mean value and standard deviation of the time-domain peak-to-peak value of the leakage current, and add them all to the feature extraction result.

14. A motor fault diagnosis device, characterized in that, It includes: A memory, configured to store a computer program; A processor, configured to execute the computer program to implement the steps of the motor fault diagnosis method according to any one of claims 1 to 9.

15. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the motor fault diagnosis method according to any one of claims 1 to 9 are implemented.

Images