Health level assessment method, storage medium, and electronic device

Abstract

The present invention relates to the technical field of assessment, and in particular to a health level assessment method, a storage medium, and an electronic device. According to the method, rotating speed feature parameters capable of directly reflecting the rotating speed state of a motor are used as comparison parameters for assessment of the health state of the motor. Specifically, the rotating speed feature parameters can be obtained on the basis of data collected in a duration in which detection is required; and the rotating speed feature parameters are compared with standard rotating speed feature parameters in a healthy operation state as a reference to obtain the difference of the distribution rule of the rotating speed feature parameters and the standard rotating speed feature parameters, thereby obtaining the instant health state of the motor in said duration. On the basis of the method, the instant health state of a motor can be accurately detected.

Description

Health assessment method, storage medium and electronic device

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on September 27, 2023, with application number 202311279483.9 and invention name “Health Assessment Method, Storage Medium and Electronic Device”. The entire contents of the above patent are incorporated into this application by reference. Technical Field

[0002] The present invention relates to the field of assessment technology, and in particular to a health assessment method, a storage medium, and an electronic device. Background Art

[0003] Asynchronous motors are the power source for electronic and mechanical equipment. They are widely used in a variety of machinery, including mining machinery, new energy vehicles, steel mill machinery, and chemical pumps, providing power and ensuring normal operation. In practical applications, asynchronous motors inevitably degrade over time. These degradations can occur due to electrical faults such as inter-turn short circuits, current imbalance, and winding breaks, as well as mechanical faults such as air gap eccentricity and bearing failure. The severity of these faults can have varying degrees of impact on the normal operation of the asynchronous motor. Therefore, the health of asynchronous motors is closely linked to the efficiency and safety of industrial production.

[0004] However, current methods for detecting whether an asynchronous motor is faulty are generally not accurate.

[0005] Summary of the Invention

[0006] The embodiments of the present invention provide a health assessment method, a storage medium, and an electronic device, which can obtain a relatively accurate difference between the instantaneous operating state and the healthy operating state of a motor.

[0007] In the first aspect, an embodiment of the present invention provides a health assessment method, in which a first speed characteristic parameter (i.e., a speed characteristic parameter within the time period that needs to be detected) is obtained through data collected from the motor during a first time period (i.e., a time period that needs to be detected), and the first speed characteristic parameter within the first time period is compared with a standard speed characteristic parameter serving as a benchmark to obtain the difference between the two, thereby obtaining the health status (i.e., health) of the motor within the first time period.

[0008] It is understood that regardless of any electrical or mechanical faults occurring in a motor, its health status can be directly reflected in its speed. Therefore, the aforementioned health assessment method uses speed characteristic parameters, which directly reflect the motor's speed status, as comparison parameters for assessing motor health. This allows for a more accurate comparison of the motor's immediate health status with its healthy operating state, even when available benchmark data lacks comprehensive coverage of fault types or insufficient data for each fault type.

[0009] In a possible implementation of the first aspect above, the first speed characteristic parameter may include an equivalent slip within a first time period, an equivalent speed ratio within a first time period, and an equivalent acceleration ratio within a first time period. That is, the first speed characteristic parameter may include an equivalent slip of the motor within a time period that needs to be detected, an equivalent speed ratio of the motor within a time period that needs to be detected, and an equivalent acceleration ratio of the motor within a time period that needs to be detected. Furthermore, the standard speed characteristic parameter serving as a benchmark may include an equivalent slip within a second time period, an equivalent speed ratio within a second time period, and an equivalent acceleration ratio within a second time period. That is, the standard speed characteristic parameter may include an equivalent slip within any time period when the motor is in a healthy operating state, an equivalent speed ratio within any time period when the motor is in a healthy operating state, and an equivalent acceleration ratio within any time period when the motor is in a healthy operating state.

[0010] It is understood that in one possible implementation, the speed characteristic parameters of a motor in a healthy operating state, such as any period of time during the motor's warranty period, can be used as standard speed characteristic parameters. Therefore, the standard speed characteristic parameters can reflect the healthy operating state of the motor. By comparing the speed characteristic parameters of the motor during the period to be tested with the standard speed characteristic parameters, a more accurate understanding of the motor's healthy state during the period to be tested and the difference between the motor's healthy operating state and the motor's healthy state can be obtained.

[0011] In a possible implementation of the first aspect above, the equivalent slip may be equal to the difference between the actual speed of the motor and the theoretical speed of the motor in a first case (i.e., when the theoretical speed of the motor and the actual speed of the motor are constant values). Similarly, the equivalent speed ratio may be equal to the ratio between the actual speed of the motor and the theoretical speed of the motor in a case where the theoretical speed of the motor and the actual speed of the motor are constant values. The equivalent acceleration ratio may be equal to the ratio between the actual acceleration of the motor and the theoretical acceleration sent by the controller of the motor in a second case (i.e., when the theoretical speed of the motor and the actual speed of the motor are not constant values).

[0012] It is understood that during the operation of a motor, there may be situations where the theoretical speed and actual speed remain constant, or there may be situations where the theoretical speed and actual speed change. The above evaluation method subdivides the motor operation process into different situations based on the change in speed to obtain corresponding speed characteristic parameters, thereby improving the accuracy of the overall evaluation.

[0013] In a possible implementation of the first aspect above, when obtaining the health of the motor within the time period that needs to be detected, the first speed characteristic parameter (i.e., the speed characteristic parameter within the time period that needs to be detected) and the distribution difference of the standard speed characteristic parameter as a benchmark can be first obtained in each working scene; then, within a certain confidence range (i.e., the preset confidence range below), the data of the speed characteristic parameter within the time period that needs to be detected in each working scene and the distribution ratio of all the speed characteristic parameter data within the time period that needs to be detected are obtained; then, based on the aforementioned distribution difference and distribution ratio, the health of the motor within the time period that needs to be detected can be obtained. Each working scene is a scene with the same working condition.

[0014] It can be understood that the distribution difference of each speed characteristic parameter (one of the equivalent slip, equivalent speed ratio and equivalent acceleration ratio) within two time periods under each identical working condition can be used to obtain the difference between the distribution of each speed characteristic parameter within the time period to be detected under each working condition and the distribution of each speed characteristic parameter in the standard speed characteristic parameter. Then, based on the distribution of each speed characteristic parameter within the time period to be detected as needed, in each working condition (i.e., the distribution ratio), the overall distribution difference between the speed characteristic parameter within the time period to be detected and the standard speed characteristic parameter can be obtained, that is, the health within the time period to be detected.

[0015] The above health assessment method can obtain the difference in the overall distribution law of the two time periods by obtaining the distribution law of the speed characteristic parameters under different working conditions. It can obtain a more accurate health status within the time period that needs to be tested and the difference with the healthy operating status corresponding to the standard speed characteristic parameters.

[0016] In a possible implementation of the first aspect above, the same operating condition includes: having the same theoretical speed or the same average value of the theoretical speed, the same gear and the same torque; or having the same theoretical speed or the same average value of the theoretical speed, and the same torque; or having the same gear and the same torque.

[0017] It can be understood that the distribution law of the rotational speed characteristic parameters can be obtained based on different division principles, such as the same working condition, so that the distribution law of the rotational speed characteristic parameters obtained is more accurate.

[0018] In a possible implementation of the first aspect above, the distribution difference between the first speed characteristic parameter (i.e., the speed characteristic parameter within the time period that needs to be detected) and the standard speed characteristic parameter (i.e., the speed characteristic parameter within any time period when the motor is in a healthy operating state) in each working scene can be obtained by the following method, including: obtaining the distribution center of the equivalent slip within the first time period, the distribution center of the equivalent speed ratio within the first time period, and the distribution center of the equivalent acceleration ratio within the first time period corresponding to the first speed characteristic parameter in each working scene; obtaining the distribution center of the equivalent slip within the second time period, the distribution center of the equivalent speed ratio within the second time period, and the distribution center of the equivalent acceleration ratio within the second time period corresponding to the standard speed characteristic parameter in each working scene. Obtain, in each working scenario, a first distance between the distribution center of the equivalent slip in the first time length and the distribution center of the equivalent slip in the second time length; obtain, in each working scenario, a second distance between the distribution center of the equivalent speed ratio in the first time length and the distribution center of the equivalent speed ratio in the second time length; obtain, in each working scenario, a third distance between the distribution center of the equivalent acceleration ratio in the first time length and the distribution center of the equivalent acceleration ratio in the second time length.

[0019] It can be understood that by obtaining the distance between the distribution centers of the characteristic parameters in each identical working scene, that is, under each identical working condition, the distribution difference of each characteristic parameter can be obtained.

[0020] In a possible implementation of the first aspect above, the data of the first speed characteristic parameter in each working scene within a first confidence range (i.e., a preset confidence range) and the distribution ratio of the data of the first speed characteristic parameter in all working scenes can be obtained by the following method, including: obtaining the data of the equivalent slip in each working scene within the first time length, the distance from the distribution center of each working scene, the number of samples within the first confidence range, and the first ratio of the total number of samples of the equivalent slip in each working scene within the first time length; obtaining the data of the equivalent speed ratio in each working scene within the first time length, the distance from the distribution center of each working scene, the number of samples within the first confidence range, and the second ratio of the total number of samples of the equivalent speed ratio in each working scene within the first time length; obtaining the data of the equivalent acceleration ratio in each working scene within the first time length, the distance from the distribution center of each working scene, the number of samples within the first confidence range, and the third ratio of the total number of samples of the equivalent acceleration ratio in each working scene within the first time length.

[0021] It can be understood that the distribution pattern of each characteristic parameter of each working scene (various working conditions) can be statistically analyzed by setting the signal range.

[0022] In a possible implementation of the first aspect above, the following method can be used to obtain the health of the motor in the first time period based on the distribution difference between the first speed characteristic parameter (i.e., the speed characteristic parameter within the time period that needs to be detected) and the standard speed characteristic parameter (i.e., the speed characteristic parameter within any time period when the motor is in a healthy operating state); and the data of the speed characteristic parameter within the time period that needs to be detected in each working scene, and the distribution proportion of all the speed characteristic parameter data within the time period that needs to be detected, including: according to the first distance and the first proportion in each working scene, obtaining the equivalent slip within the first time period of all working scenes, and the equivalent slip within the second time period The first statistical difference of the equivalent slip; according to the second distance and the second proportion in each working scene, the second statistical difference of the equivalent speed ratio in the first time length and the equivalent speed ratio in the second time length are obtained for all working scenes; according to the third distance and the third proportion in each working scene, the third statistical difference of the equivalent acceleration ratio in the first time length and the equivalent acceleration ratio in the second time length are obtained for all working scenes; according to the first statistical difference, the second statistical difference, the third statistical difference, and the weight coefficients corresponding to the equivalent slip, the weight coefficient corresponding to the equivalent speed ratio, and the weight coefficient corresponding to the equivalent acceleration ratio, the health of the motor in the first time length is obtained.

[0023] It can be understood that the health of the motor within the time period that needs to be detected can be obtained by summarizing the distribution differences of various characteristic parameters in the two time periods.

[0024] In one possible implementation of the first aspect, the first confidence range includes any one of: [-3σ, 3σ], [-2σ, 2σ], and [-σ, σ], where σ represents the standard deviation of each parameter in the first speed characteristic parameter, for example, σ represents the standard deviation of the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio in the first speed characteristic parameter. It will be appreciated that the first confidence range, also known as the preset confidence range, can be adjusted based on specific needs, such as based on the desired accuracy of the assessment results, to obtain a more accurate health assessment result.

[0025] In a second aspect, an embodiment of the present invention provides a health assessment device, comprising one or more processors and one or more memories; the one or more memories are coupled to the one or more processors, and the one or more memories are used to store computer program code, the computer program code including computer instructions, and when the one or more processors execute the computer instructions, the device executes any one of the health assessment methods provided in the first aspect and various possible implementations of the first aspect.

[0026] In a third aspect, an embodiment of the present invention provides a chip, which includes a processor, and the processor executes computer instructions stored in a computer storage medium, so that the electronic device can implement any health assessment method provided by various possible implementations of the first aspect mentioned above.

[0027] In a fourth aspect, an embodiment of the present invention provides a readable storage medium having instructions stored thereon, which, when executed on an electronic device, enables the electronic device to implement any one of the health assessment methods provided by the various possible implementations of the first aspect mentioned above.

[0028] In a fifth aspect, an embodiment of the present invention provides an electronic device, comprising: a memory for storing instructions executed by one or more processors of the electronic device; and a processor, which is one of the processors of the electronic device, for executing the instructions stored in the memory to implement any one of the health assessment methods provided by the various possible implementations of the first aspect above.

[0029] In a sixth aspect, an embodiment of the present invention provides a program product, which includes instructions. When the instructions are executed by an electronic device, the electronic device can implement any health assessment method provided by various possible implementations of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] FIG1A is a schematic diagram showing a flow chart of a method for detecting whether an electrical fault occurs in a motor using a fault diagnosis model according to some embodiments of the present invention;

[0031] FIG1B is a flow chart illustrating a method for detecting a mechanical fault of a motor using a fault signature library matching method according to some embodiments of the present invention;

[0032] FIG2 shows a schematic diagram of software modules of a health assessment system according to some embodiments of the present invention;

[0033] FIG3 is a schematic diagram showing a flow chart of a health assessment method according to some embodiments of the present invention;

[0034] FIG4 is a flow chart showing another health assessment method according to some embodiments of the present invention;

[0035] FIG5A shows a time domain schematic diagram of a set of current signals according to some embodiments of the present invention;

[0036] FIG5B shows a schematic diagram of a time-frequency analysis of a set of current signals according to some embodiments of the present invention;

[0037] FIG5C shows a frequency spectrum diagram of a set of current signals according to some embodiments of the present invention;

[0038] FIG5D shows a time domain diagram of a set of vibration signals according to some embodiments of the present invention;

[0039] FIG5E shows a spectrum diagram of a set of vibration signals according to some embodiments of the present invention;

[0040] FIG5F is a schematic diagram showing a comparison of theoretical speeds and actual speeds of a group of asynchronous motors according to some embodiments of the present invention;

[0041] FIG5G shows a time domain schematic diagram of another set of current signals according to some embodiments of the present invention;

[0042] FIG5H shows a time-frequency diagram of another set of asynchronous motors according to some embodiments of the present invention;

[0043] FIG5I is a time domain diagram illustrating another set of vibration signals according to some embodiments of the present invention;

[0044] FIG5J shows a time-frequency diagram of another set of asynchronous motors according to some embodiments of the present invention;

[0045] FIG6 shows a schematic diagram of the hardware structure of an electronic device according to some embodiments of the present invention. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be described clearly and in detail below with reference to the accompanying drawings.

[0047] Illustrative embodiments of the present invention include, but are not limited to, a health assessment method, a storage medium, and an electronic device.

[0048] The following first explains the terms involved in this application.

[0049] (1) Asynchronous motor: also known as induction motor, is an AC motor that converts electromechanical energy into mechanical energy by generating electromagnetic torque through the interaction between the rotating magnetic field in the air gap and the induced current in the rotor winding.

[0050] The technical solution of the present invention is described below with reference to FIG. 1A to FIG. 6 .

[0051] As described in the background art, some current methods for detecting whether an asynchronous motor is faulty are generally not very accurate.

[0052] For example, in some detection methods, a fault diagnosis model is used to detect whether an asynchronous motor has a fault. FIG1A shows a method for detecting whether a motor has an electrical fault using a fault diagnosis model. As shown in FIG1A , the steps of this detection method include:

[0053] S101, obtaining historical operating electrical fault data of the motor to be tested.

[0054] S102 , using the current signal in the historical electrical fault data as input data and the electrical fault of the motor to be tested as output data, to train a fault diagnosis model and obtain a trained fault diagnosis model.

[0055] It is understood that when an asynchronous motor experiences an electrical fault, it will exhibit abnormal characteristics, such as current imbalance, voltage imbalance, and a significant increase in the motor's negative-sequence impedance. Therefore, the current signal collected by the current sensor installed on the motor under test from historical operating electrical fault data can be obtained and used as input data. A reference value for determining that the motor under test has an electrical fault is set to 1, and a reference value for determining that the motor under test has not experienced an electrical fault is set to 0, to train a fault diagnosis model. The fault diagnosis model can include a convolutional neural network model, a random forest fault diagnosis model, and the like.

[0056] S103 , inputting the real-time electrical data of the motor to be tested into the trained fault diagnosis model to determine whether the motor to be tested has an electrical fault.

[0057] It can be understood that after obtaining the real-time electrical data of the motor, the current signal in the real-time electrical data can be input into the trained fault diagnosis model, and then based on the output result of the fault diagnosis model, it is determined whether the motor to be tested has an electrical fault.

[0058] It is understandable that the historical operating electrical fault data only corresponds to electrical faults. Therefore, if a fault diagnosis model is needed to detect whether a motor has a mechanical fault, the fault diagnosis model can be trained based on the historical operating mechanical fault data of the motor.

[0059] It is understood that the accuracy of methods for detecting electrical or mechanical faults in asynchronous motors based on fault diagnosis models depends on factors such as whether the training dataset covers a comprehensive range of operating conditions and application scenarios, as well as the adequacy of the training data for each operating condition and application scenario. For example, the historical electrical fault data used to train the fault diagnosis model must include sufficient historical electrical fault data under various torque conditions and correspond to the same application scenario, which can include mining scenarios, road driving scenarios, and so on.

[0060] Therefore, if the historical operating electrical fault data or historical operating vibration fault data used to train the fault diagnosis model does not cover all the working conditions and application scenarios, or the amount of training data in any working condition and application scenario is insufficient, etc., then the method of using the fault diagnosis model to detect whether the asynchronous motor has an electrical fault or a mechanical fault will also have a low accuracy in the detection results.

[0061] In other detection methods, a fault signature library matching method is used to detect whether an asynchronous motor has a fault. FIG1B shows a method for detecting a mechanical fault of a motor using a fault signature library matching method. As shown in FIG1B , the steps of this detection method include:

[0062] S111, obtaining historical operating vibration fault data of the motor to be tested.

[0063] S112 , performing feature decomposition on vibration signals in historical operating vibration fault data to obtain a fault feature library.

[0064] It is understandable that the historical operating vibration fault data can be feature decomposed, and a fault feature library can be obtained based on the fault features obtained by the decomposition, such as the residual of the amplitude of the vibration signal, the intensity of the vibration, etc.

[0065] S113, obtaining an actual vibration signal of the motor to be tested.

[0066] S114 , matching the fault feature in the actual vibration signal with the fault feature library to determine whether a mechanical fault occurs in the motor to be tested.

[0067] It is understood that the actual vibration signal can be feature decomposed to obtain the residual of the actual vibration signal's amplitude, vibration intensity, etc. The residual of the actual vibration signal's amplitude, vibration intensity, etc. are then matched with the fault features in the fault feature library. Based on the matching results, it is determined whether the motor under test has a mechanical fault.

[0068] It is understandable that because historical mechanical fault data only corresponds to mechanical faults, if a fault signature library matching method is needed to detect whether an asynchronous motor has an electrical fault, a fault signature library, such as a current signal, needs to be re-established based on the motor's historical electrical fault data.

[0069] It can be understood that the accuracy of the method for detecting whether an asynchronous motor has a mechanical fault or an electrical fault based on the fault feature library depends on whether the fault feature is accurately extracted, whether the operating conditions and application scenarios covered by the historical operating electrical fault data or the historical operating vibration fault data are comprehensive, and whether the amount of data in each operating condition and application scenario is sufficient, and whether it includes enough types of fault features.

[0070] For example, if a motor is operating in a complex environment and has a mechanical fault such as poor lubrication, the vibration signal intensity may not change significantly, making it difficult to extract the vibration signal intensity, or in other words, the fault signature of the vibration signal. Alternatively, due to the low level of industrial penetration of three-phase current and voltage sensors, it is difficult to obtain voltage and current data for all three phases, resulting in incomplete fault signatures extracted from single-phase current and voltage data. Alternatively, when an abnormality such as increased internal resistance occurs in the motor, the current and voltage signals may not show obvious abnormalities, making it difficult to extract the fault signatures of the current and voltage signals. Therefore, the accuracy of the detection results obtained by the method of detecting whether an asynchronous motor has an electrical or mechanical fault based on a fault signature library is also low.

[0071] Moreover, if the historical operating vibration fault data or historical operating electrical fault data used to establish the fault feature library do not cover all the working conditions and application scenarios, or the amount of data in any one working condition and application scenario is insufficient, or the number of types of fault features of the data in any one working condition and application scenario is insufficient, then the method of detecting whether the asynchronous motor has an electrical fault or a mechanical fault based on the fault feature library will also have a low accuracy in the detection results obtained.

[0072] In view of this, the present invention proposes a method for evaluating the health of a motor. In this method, the speed characteristic parameters (hereinafter referred to as characteristic parameters) of the training data set (i.e., data collected when the asynchronous motor is in a healthy operating state, such as data collected during the warranty period of the asynchronous motor) and the test data set (i.e., data collected during the time period that the asynchronous motor needs to be tested) corresponding to each working scene can be obtained respectively. Among them, the characteristic parameters are used to characterize the speed state of the asynchronous motor, including equivalent slip, equivalent speed ratio and equivalent acceleration ratio. Then, the characteristic parameters of the training data set and the test data set in each working scene (i.e., the distribution areas mentioned later) are compared to obtain the distribution differences of the distribution laws of the characteristic parameters of the training data set and the test data set in each working scene. Then, the health of the motor can be determined based on the distribution differences of the distribution laws of the characteristic parameters of the training data set and the test data set in each working scene. For example, the distribution difference of the distribution rules of the characteristic parameters of the training data set and the test data set in each working scenario can be obtained; the distribution ratio of the characteristic parameters of the training data set in each working scenario in the characteristic parameters of the entire training data set can be obtained based on the preset confidence range; the distribution ratio of the characteristic parameters of the test data set in each working scenario in the characteristic parameters of the entire test data set can be obtained based on the preset confidence range; and the health status of the motor, that is, the specific numerical value of the health of the asynchronous motor corresponding to the test data set, can be obtained based on the weight of each characteristic parameter.

[0073] It is understandable that regardless of any type of fault (e.g., any electrical fault or any mechanical fault) in an asynchronous motor, its health status will be directly reflected in its speed, such as the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio in its characteristic parameters. Therefore, by comparing the characteristic parameters of asynchronous motors, it is possible to obtain a more accurate assessment of the health of the asynchronous motor, even when the baseline data (i.e., training dataset) contains an incomplete list of fault types or the data volume for each fault type is insufficient. This means comparing the asynchronous motor's immediate health status with its healthy operating state.

[0074] It is understood that each working scenario of the asynchronous motor has the same theoretical speed or the same average theoretical speed, the same gear, and the same torque; or each working scenario has the same theoretical speed or the same average theoretical speed and the same torque; or each working scenario has the same gear and the same torque. It is understood that the working scenarios, that is, the principle of dividing the distribution area of ​​the characteristic parameters, are divided according to the same working conditions and other conditions, so that each characteristic parameter in the training data set can be compared with the corresponding characteristic parameter in the test data set in the same working scenario.

[0075] It can be understood that the equivalent slip of the asynchronous motor is equal to the difference between the actual speed of the asynchronous motor and the theoretical speed sent by the controller of the asynchronous motor in the first case. The equivalent speed ratio is equal to the ratio between the actual speed of the asynchronous motor and the theoretical speed sent by the controller of the asynchronous motor in the first case. The equivalent acceleration ratio is equal to the ratio between the actual acceleration of the asynchronous motor and the theoretical acceleration sent by the controller of the asynchronous motor in the second case. In the first case, that is, the asynchronous motor is in a stable state, the theoretical speed and actual speed of the asynchronous motor are constant values. In the second case, that is, the asynchronous motor is in a non-steady state, the theoretical speed and actual speed of the asynchronous motor are not constant values.

[0076] In one possible implementation, a method for obtaining the health of an asynchronous motor corresponding to a test dataset may include: first, obtaining three characteristic parameters of the training dataset, including data on equivalent slip, equivalent speed ratio, and equivalent acceleration ratio, and three characteristic parameters of the test dataset, including data on equivalent slip, equivalent speed ratio, and equivalent acceleration ratio. Then, within each working scenario, obtaining the distribution differences of the three characteristic parameters of the training dataset and the test dataset, such as the difference between the equivalent slip of the training dataset and the equivalent slip of the test dataset within each working scenario; the difference between the equivalent speed ratio of the training dataset and the equivalent speed ratio of the test dataset within each working scenario; and the difference between the equivalent acceleration ratio of the training dataset and the equivalent speed ratio of the test dataset within each working scenario. Then, within a preset confidence range, the number of samples of the characteristic parameter data of the training dataset within each working scenario, the distribution ratio of the characteristic parameter data of the entire training dataset, and the distribution ratio of the characteristic parameter data of the test dataset within each working scenario within the entire test dataset can be calculated. Then, based on the differences in the three characteristic parameters of the training dataset and the test dataset in each working scenario, the distribution ratio of the characteristic parameters of the training dataset in each working scenario within the preset signal range in the data of the entire training dataset, and the distribution ratio of the characteristic parameters of the test dataset in each working scenario within the preset signal range in the data of the entire test dataset, the statistical difference of the equivalent slip of the training dataset and the test dataset of all working scenarios, the statistical difference of the equivalent speed ratio of the training dataset and the test dataset of all working scenarios, and the statistical difference of the equivalent acceleration ratio of the training dataset and the test dataset of all working scenarios are obtained. Finally, based on the weight of each characteristic parameter, the statistical difference of the equivalent slip of the training dataset and the test dataset of all working scenarios, the statistical difference of the equivalent speed ratio of the training dataset and the test dataset of all working scenarios, and the statistical difference of the equivalent acceleration ratio of the training dataset and the test dataset of all working scenarios, the specific value of the health of the asynchronous motor corresponding to the test dataset can be obtained.

[0077] It can be understood that the data in the training data set can reflect the working state of the asynchronous motor in a healthy operating state. Therefore, by comparing the characteristic parameters corresponding to the test data set with the characteristic parameters corresponding to the test data set, the working state corresponding to the data of the test data set can be obtained, and the comparison results with the healthy operating state of the asynchronous motor can be obtained.

[0078] It will be appreciated that in some embodiments, if a fault diagnosis model is required to detect whether an asynchronous motor has an electrical or mechanical fault, then the fault diagnosis model must be trained based on both the motor's historical electrical fault data and the motor's historical mechanical fault data. In other words, the same fault diagnosis model cannot be used to detect both electrical and mechanical faults. Furthermore, the accuracy of the method for detecting whether an asynchronous motor has an electrical or mechanical fault based on the fault diagnosis model depends on the comprehensiveness of the operating conditions and application scenarios covered by the training dataset, as well as the adequacy of the amount of training data for each operating condition and application scenario.

[0079] It is understood that in other embodiments, if a fault feature library matching method is required to detect whether an asynchronous motor has an electrical fault or a mechanical fault, then it is necessary to establish a fault feature library, such as a current signal, based on the motor's historical electrical fault data, and to establish a fault feature library, such as a vibration signal, based on the motor's historical mechanical fault data. In other words, the same fault feature library cannot be used to detect both electrical faults and mechanical faults. Furthermore, the accuracy of the method for detecting whether an asynchronous motor has a mechanical fault or an electrical fault based on the fault feature library depends on whether the fault feature extraction is accurate, whether the operating conditions and application scenarios covered by the historical electrical fault data or the historical vibration fault data are comprehensive, and whether the amount of data in each operating condition and application scenario is sufficient, and whether it includes enough types of fault features.

[0080] It is understandable that any type of fault in an asynchronous motor, including electrical faults and mechanical faults, as well as other possible faults, may directly cause the speed state of the asynchronous motor to be different from the speed state of the asynchronous motor in a healthy operating state. That is, when a fault occurs, the characteristic parameters representing the speed state of the asynchronous motor, including the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio, have distribution differences compared to the characteristic parameters representing the speed state of the asynchronous motor in a healthy operating state, including the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio, thereby affecting the normal use of the asynchronous motor. Therefore, the above-mentioned motor health assessment method based on characteristic parameters does not need to extract the characteristics of all types of faults, nor does it need to consider whether the data used as a benchmark includes enough types of fault characteristics, and can also obtain more accurate detection results. By comparing the characteristic parameters of the asynchronous motor, a more accurate difference between the immediate health state and the healthy operating state of the asynchronous motor can be obtained even when the application scenario is not comprehensive or the amount of data is insufficient.

[0081] The aforementioned health assessment method can accurately assess the difference between the asynchronous motor's current and healthy operating states by comparing the distribution differences between the characteristic speed parameters of the asynchronous motor's healthy operating state in the training dataset and the characteristic speed parameters of the asynchronous motor's current operating state in the test dataset. Furthermore, by storing these parameters in separate files, this method provides a precise and comprehensive reference for subsequent lifespan and degradation prediction of the asynchronous motor.

[0082] A health assessment method of the present invention will be described below with reference to FIG. 2 , FIG. 3 , FIG. 4 , FIG. 5A to FIG. 5J , and FIG. 6 .

[0083] In the embodiments of the present application, an asynchronous motor will be used as an example for description. Other devices with similar functions can also be applied to the health assessment method of the present application. The embodiments of the present application do not specifically limit the type of device applied to the health assessment method of the present application.

[0084] Figure 2 shows a schematic diagram of software modules of a health assessment system for implementing the health assessment method of the present application. As shown in Figure 2, a health assessment system may include: an information collection module 210, a feature calculation module 220, a health assessment module 230, and a data archiving module 240.

[0085] The information acquisition module 210 is used to collect the vibration signal, current signal, torque signal, and gear signal of the asynchronous motor, and transmits the collected vibration signal, current signal, torque signal, and gear signal of the asynchronous motor to the feature calculation module 220. The information acquisition module 210 includes a vibration signal acquisition module 211, a current signal acquisition module 212, a torque signal acquisition module 213, and a gear signal acquisition module 214. The vibration signal acquisition module 211 is used to receive the vibration signal of the asynchronous motor collected and transmitted by a vibration acceleration sensor or a vibration velocity sensor. The current signal acquisition module 212 is used to receive the current signal of the asynchronous motor collected and transmitted by a current sensor. The torque signal acquisition module 213 is used to receive the torque signal of the asynchronous motor collected and transmitted by a torque sensor. The gear signal acquisition module 214 is used to receive the gear signal of the asynchronous motor transmitted by the asynchronous motor control system. For example, the gear signal of the asynchronous motor may include first gear, second gear, and third gear, where first gear corresponds to the rated speed of 15 rpm, second gear corresponds to the rated speed of 25 rpm, and third gear corresponds to the rated speed of 35 rpm. Each gear corresponds to a different rated speed.

[0086] In one possible implementation, the information acquisition module 210 may include only the vibration signal acquisition module 211, the current signal acquisition module 212, and the gear signal acquisition module 214; or may include only the vibration signal acquisition module 211 and the current signal acquisition module 212. In the embodiment of the present application, the type and number of modules in the information acquisition module 210 are not specifically limited.

[0087] It is understood that current sensors, vibration acceleration sensors, vibration velocity sensors, torque sensors, and other sensors that can be used to collect various signals can be installed on the asynchronous motor. In the embodiments of the present application, there is no specific limitation on the type of sensor used and the installation location of the sensor.

[0088] The feature calculation module 220 is used to calculate the theoretical speed, actual speed, equivalent slip, equivalent speed ratio, and equivalent acceleration ratio of the asynchronous motor, and transmits the acquired torque signal, gear position signal, theoretical speed, actual speed, equivalent slip, equivalent speed ratio, and equivalent acceleration ratio of the asynchronous motor to the health assessment module 230. The equivalent slip of the asynchronous motor is equal to the difference between the actual speed of the asynchronous motor and the theoretical speed sent by the asynchronous motor controller. The equivalent speed ratio is equal to the ratio between the actual speed of the asynchronous motor and the theoretical speed sent by the asynchronous motor controller. The equivalent acceleration ratio is equal to the ratio between the actual acceleration of the asynchronous motor and the theoretical acceleration sent by the asynchronous motor controller. The feature calculation module 220 includes a theoretical speed and actual speed calculation module 221, an equivalent slip calculation module 222, an equivalent speed ratio calculation module 223, and an equivalent acceleration ratio calculation module 224.

[0089] The theoretical speed and actual speed calculation module 221 is configured to calculate the actual speed based on the asynchronous motor's vibration signal acquired by the vibration signal acquisition module 211, and the theoretical speed based on the asynchronous motor's current signal acquired by the current signal acquisition module 212. The equivalent slip calculation module 222 is configured to calculate the equivalent slip based on the theoretical speed and actual speed calculated by the theoretical speed and actual speed calculation module 221. The equivalent speed ratio calculation module 223 is configured to calculate the equivalent speed ratio based on the theoretical speed and actual speed acquired by the theoretical speed and actual speed calculation module 221 in a first scenario. The equivalent acceleration ratio calculation module 224 is configured to calculate the equivalent acceleration ratio based on the theoretical speed and actual speed acquired by the theoretical speed and actual speed calculation module 221 in a second scenario. In the first scenario, the asynchronous motor is in a steady state, meaning that the theoretical speed and actual speed of the asynchronous motor are constant. In the second scenario, the asynchronous motor is in a non-steady state, meaning that the theoretical speed and actual speed of the asynchronous motor are not constant.

[0090] The health assessment module 230 is configured to calculate the health of the asynchronous motor based on the asynchronous motor's torque signal, gear signal, theoretical speed, actual speed, equivalent slip, equivalent speed ratio, and equivalent acceleration ratio sent by the feature calculation module 220. The module then sends the gear, torque, health, theoretical speed, equivalent slip, equivalent speed ratio, and equivalent acceleration ratio of the asynchronous motor to the data profiling module 240. The health assessment module 230 includes a gear acquisition module 231, a torque acquisition module 232, a health calculation module 233, and a health normalization module 234. The gear acquisition module 231 is configured to receive the asynchronous motor's gear signal sent by the feature calculation module 220. The torque acquisition module 232 is configured to receive the asynchronous motor's torque signal sent by the feature calculation module 220. The health calculation module 233 is configured to calculate the health of the asynchronous motor based on the torque signal, gear signal, theoretical speed, actual speed, equivalent slip, equivalent speed ratio, and equivalent acceleration ratio of the asynchronous motor sent by the feature calculation module 220. The health normalization module 234 is used to clear the previous health information before the health calculation module 233 calculates the current health. The method for calculating the health of the asynchronous motor by the health calculation module 233 will be described in detail below with reference to FIG4 .

[0091] The data archiving module 240 is used to create a file based on the gear position, torque, theoretical speed, health, equivalent slip, equivalent speed ratio, and equivalent acceleration ratio data sent by the health assessment module 230. The data archiving module 240 includes a health archiving module 241, an equivalent slip archiving module 242, an equivalent acceleration ratio archiving module 243, an equivalent speed ratio archiving module 244, and a theoretical speed and torque archiving module 245. The health archiving module 241 is used to store the health data of the asynchronous motor sent by the health assessment module 230. The equivalent slip archiving module 242 is used to store the equivalent slip data of the asynchronous motor sent by the health assessment module 230. The equivalent acceleration ratio archiving module 243 is used to store the equivalent acceleration ratio data of the asynchronous motor sent by the health assessment module 230. The equivalent speed ratio archiving module 244 is used to store the equivalent speed ratio data of the asynchronous motor sent by the health assessment module 230. The theoretical speed and torque archive module 245 is used to store the theoretical speed and torque data of the asynchronous motor sent by the health assessment module 230; or to store the gear and torque data of the asynchronous motor sent by the health assessment module 230. Furthermore, the distribution area of ​​the data in the health degree archive module 241, the equivalent slip archive module 242, the equivalent acceleration ratio archive module 243, and the equivalent speed ratio archive module 244 will correspond to the distribution area of ​​the data in the theoretical speed and torque archive module 245.

[0092] It can be understood that the above-mentioned health assessment system can evaluate the health of the asynchronous motor based on the collected vibration signal, current signal, torque signal, and gear signal of the asynchronous motor, and save the assessment results and various data in different grades, providing more accurate data support for the life prediction and degradation prediction of the asynchronous motor.

[0093] The following will introduce a health assessment method of the present invention based on a health assessment system shown in Figure 2, in conjunction with Figures 3 and 4. Figure 3 shows a flow chart of a health assessment method. As shown in Figure 3, the steps of a health assessment method may include:

[0094] S310: Obtain a training data set and a test data set for health assessment of an asynchronous motor.

[0095] It can be understood that the specific type of collected signals can be set based on the actual scenario. For example, from the perspective of saving overall costs and improving the efficiency of the evaluation, in one possible implementation, the data of the current signal and vibration signal of the asynchronous motor can be collected as the training data set and test data set for the health assessment. Alternatively, in another possible implementation, the data of the current signal, vibration signal, and gear signal of the asynchronous motor can be collected as the training data set and test data set for the health assessment. Alternatively, in another possible implementation, the data of the current signal, vibration signal, gear signal, and torque signal of the asynchronous motor can be collected as the training data set and test data set for the health assessment. In this application, there is no specific limitation on the type of collected signals.

[0096] It is understood that the collection duration of the training and test datasets for current signals can be set based on actual circumstances. For example, it can be set based on the healthy operating status of the asynchronous motor, such as the warranty period of the asynchronous motor. If the warranty period of the asynchronous motor is 12 months, then the collection duration of the training dataset for current signals can be set to within 12 months of normal operation of the asynchronous motor after leaving the factory, and the collection duration of the test dataset for current signals can be set to between 12 months and 24 months after the asynchronous motor leaves the factory.

[0097] In one possible implementation, the training dataset can be collected over a period of three months or longer, thereby providing sufficient data for evaluating the health of the asynchronous motor and improving the accuracy of the health of the asynchronous motor. In this application, there is no specific limitation on the collection period of the training and test datasets for the current signal.

[0098] It is understood that a current clamp can be installed in the asynchronous motor to collect the single-phase current signal x(t) in the frequency converter cabinet of the asynchronous motor. In the embodiments of the present application, there is no specific limitation on the device used to collect the current signal of the asynchronous motor.

[0099] For example, 50 sets of current signals can be collected within every 24 hours, with each set of current signals collected for 2 seconds, and the collection interval between each adjacent set of current signals is greater than or equal to 20 minutes. It is understood that the total time for collecting current signals, the number of sets of current signals collected, the collection duration of each set of current signals, and the collection interval between each adjacent set of current signals can all be set based on specific scenarios and needs. In the embodiments of the present application, the specific values ​​of the aforementioned parameters are not specifically limited.

[0100] It's understood that the parameters for collecting vibration signals and current signals, such as time, frequency, and duration, are identical. This means that the vibration and current signals are collected at the same time, using the same frequency and duration. The collection durations for the training and test datasets for the vibration signals can be set to match those for the current signals, depending on actual needs.

[0101] For example, it can also be set according to the warranty period of the asynchronous motor. If the warranty period of the asynchronous motor is 12 months, then the collection time of the training data set of the vibration signal can be set to within 12 months of normal operation of the asynchronous motor after leaving the factory, and the collection time of the test data set of the vibration signal can be set to between 12 months and 24 months after the asynchronous motor leaves the factory. In this application, there is no specific limitation on the collection time of the training data set and the test data set of the vibration signal.

[0102] It is understood that a vibration acceleration sensor or a vibration velocity sensor can be installed in the asynchronous motor to collect the vibration signal y(t) of the asynchronous motor. For example, 50 groups of vibration signals can be collected within every 24 hours, and the collection time of each group of vibration signals is 2 seconds, and the collection interval time of every two adjacent groups of vibration signals is greater than or equal to 20 minutes. It is understood that the total time for collecting vibration signals, the number of groups collecting vibration signals, the collection time of each group of vibration signals, and the collection interval time of every two adjacent groups of vibration signals can all be set according to specific scenarios and needs. In the embodiments of the present application, no specific limitation is made to the specific numerical values ​​of the aforementioned parameters.

[0103] S320, respectively calculating feature parameters corresponding to the training dataset and the test dataset.

[0104] In one possible implementation, the theoretical speed and actual speed of the asynchronous motor training dataset can be calculated based on the current signal and vibration signal of the asynchronous motor training dataset, and characteristic parameters such as the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio of the training dataset can be further calculated. Furthermore, the theoretical speed and actual speed of the asynchronous motor test dataset can be calculated based on the current signal and vibration signal of the asynchronous motor test dataset, and characteristic parameters such as the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio of the training dataset can be further calculated.

[0105] For example, in the first case, that is, when the asynchronous motor is in a stable state, that is, when the theoretical speed and the actual speed of the asynchronous motor are both constant values, the equivalent slip and the equivalent speed ratio of the asynchronous motor are calculated. In the second case, when the asynchronous motor is in a non-steady state, that is, when the theoretical speed and the actual speed of the asynchronous motor are not constant values, the equivalent acceleration ratio of the asynchronous motor is calculated. Among them, the equivalent slip is equal to the difference between the actual speed and the theoretical speed in the first case. The equivalent speed ratio is equal to the ratio between the actual speed and the theoretical speed in the first case. The equivalent acceleration ratio is equal to the ratio between the actual acceleration and the theoretical acceleration in the second case, that is, the ratio between the first-order difference of the actual speed and the first-order difference of the theoretical speed. The specific method for calculating the characteristic parameters corresponding to the training data set and the test data set will be described in detail below in conjunction with Figure 4.

[0106] S330 , calculating the healthiness corresponding to the test data set according to the characteristic parameters corresponding to the training data set and the characteristic parameters corresponding to the test data set.

[0107] In one possible implementation, the distribution differences of three characteristic parameters of the training data set and the test data set can be calculated for each working scenario, such as the distribution differences of the equivalent slip, the distribution differences of the equivalent speed ratio, and the distribution differences of the equivalent acceleration ratio. Then, the distribution ratio of the characteristic parameter data of the training data set in each working scenario within a preset confidence range to the characteristic parameter data of the entire training data set can be calculated, as well as the distribution ratio of the characteristic parameter data of the test data set in each working scenario within the preset confidence range to the characteristic parameter data of the entire test data set. Then, the distribution difference of the three characteristic parameters of the training data set and the test data set can be obtained based on each working scenario; the distribution ratio of the characteristic parameter data of the training data set in each working scenario in the data of the entire training data set within the preset confidence range; the distribution ratio of the characteristic parameter data of the test data set in each working scenario in the data of the entire test data set within the preset confidence range; obtain the statistical difference between the equivalent slip of the training data set of all working scenarios and the equivalent slip of the test data set, the statistical difference between the equivalent speed ratio of the training data set of all working scenarios and the equivalent speed ratio of the test data set, and the statistical difference between the equivalent acceleration ratio of the training data set of all working scenarios and the equivalent acceleration ratio of the test data set. Finally, the health of the asynchronous motor corresponding to the test data set can be obtained based on the weight of each characteristic parameter, the statistical difference between the equivalent slip of the training data set of all working scenarios and the equivalent slip of the test data set, the statistical difference between the equivalent speed ratio of the training data set of all working scenarios and the equivalent speed ratio of the test data set, and the statistical difference between the equivalent acceleration ratio of the training data set of all working scenarios and the equivalent acceleration ratio of the test data set.

[0108] It is understood that each working scenario of the asynchronous motor has the same theoretical speed or the same average theoretical speed, the same gear, and the same torque; or each working scenario has the same theoretical speed or the same average theoretical speed and the same torque; or each working scenario has the same gear and the same torque. It is understood that the working scenarios, that is, the principle of dividing the distribution area of ​​the characteristic parameters, are divided according to the same working conditions and other conditions, so that each characteristic parameter in the training data set can be compared with the corresponding characteristic parameter in the test data set in the same working scenario.

[0109] It can be understood that the data in the training data set can reflect the working state of the asynchronous motor in a healthy operating state. By comparing the characteristic parameters corresponding to the test data set with the characteristic parameters corresponding to the training data set, the difference between the working state corresponding to the data in the test data set and the healthy operating state of the asynchronous motor can be obtained, and the difference can be expressed as a health value. In addition, since the health state of the asynchronous motor will be directly reflected in the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio of the asynchronous motor regardless of any type of fault, the instantaneous health state of the asynchronous motor can be directly obtained by comparing the characteristic parameters such as the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio of the asynchronous motor, thereby improving the accuracy, efficiency, cost, and convenience of evaluating the health state of the asynchronous motor.

[0110] The specific method for calculating the health level corresponding to the test data set will be described in detail below in conjunction with FIG4 .

[0111] S340, storing the characteristic parameters corresponding to the training data set, the characteristic parameters corresponding to the test data set, and the health level into a file.

[0112] It can be understood that the characteristic parameters corresponding to the training data set, the characteristic parameters corresponding to the test data set and the health level can be stored in the archive, which can provide more accurate data support when the life prediction and degradation prediction of this asynchronous motor are performed later.

[0113] The aforementioned health assessment method compares the characteristic parameters of an asynchronous motor's test dataset with the characteristic parameters of its training dataset. This method can determine the difference between the operating state corresponding to the test dataset and the operating state corresponding to the asynchronous motor's training dataset, i.e., the healthy operating state of the asynchronous motor. This difference is then visually represented by a health value, thereby determining the health of the asynchronous motor's test dataset. This provides a relatively accurate reference for assessing the asynchronous motor's health. Furthermore, by storing the characteristic parameters corresponding to the training dataset, the characteristic parameters corresponding to the test dataset, and the health value in an archive, a relatively accurate reference is provided for predicting the lifespan and degradation of the asynchronous motor.

[0114] In some possible implementations, FIG4 shows a flow chart of another health assessment method. As shown in FIG4 , a health assessment method includes:

[0115] S410: Acquire a training data set and a test data set of current signals.

[0116] It can be understood that the method for obtaining the current signal can be based on step S310 in FIG. 3 , which will not be described in detail here.

[0117] S420, calculating the theoretical rotation speed.

[0118] It is understandable that the theoretical speed of the asynchronous motor for each set of current signals in the training dataset and the test dataset may be calculated based on the data in the training dataset and the test dataset of the current signals acquired in step S410 .

[0119] In one possible implementation, in the first case, the asynchronous motor is in a stable state, that is, the theoretical speed and the actual speed of the asynchronous motor are constant, or the changes in the theoretical speed and the actual speed are both less than a first threshold, such as 0.1 / s. In the embodiments of the present application, the specific value of the first threshold is not specifically limited.

[0120] For example, Figure 5A shows a time-domain schematic diagram of a set of current signals, which were collected over a 2-second period. Based on the time-domain schematic diagram of the current signals shown in Figure 5A , methods such as short-time Fourier transform can be used to obtain the current signal time-frequency analysis schematic diagram shown in Figure 5B , and methods such as Fourier transform can be used to obtain the current signal spectrum diagram shown in Figure 5C . Therefore, based on the current signal spectrum diagram shown in Figure 5C , the theoretical speed of the asynchronous motor corresponding to the current signal in Figure 5A can be obtained, i.e., the theoretical speed v0 = 15.0 Hz transmitted by the asynchronous motor controller.

[0121] It is understood that other methods can also be used to calculate the theoretical speed of the asynchronous motor, and the theoretical speeds of the asynchronous motor calculated by different methods can be compared. If the theoretical speeds of the asynchronous motors calculated based on multiple methods are equal, or the difference between the theoretical speeds of the asynchronous motors is less than a preset threshold, then the final theoretical speed of the asynchronous motor can be determined. In the embodiments of the present application, there are no specific limitations on the method for calculating the theoretical speed of the asynchronous motor and the rules for determining the theoretical speed of the asynchronous motor.

[0122] S430: Estimate the actual speed fluctuation range.

[0123] It is understood that the speed fluctuation range corresponding to each set of current signals of the asynchronous motor can be estimated based on the theoretical speed of the asynchronous motor corresponding to each set of current signals obtained in step S420. For example, if the theoretical speed v0 of the asynchronous motor is 15.0 Hz, then the speed fluctuation range of the asynchronous motor can be estimated to be [0, v0]. In the embodiments of the present application, the method for estimating the speed fluctuation range of the asynchronous motor is not specifically limited.

[0124] S440: Obtain a training data set and a test data set of vibration signals.

[0125] It can be understood that the method for obtaining the vibration signal can be based on step S310 in FIG. 3 , which will not be described in detail here.

[0126] S450, low-pass filtering calculation.

[0127] It is understood that if a vibration velocity sensor is used to acquire the vibration signal in step S440, since the sampling frequency of the vibration velocity sensor is low and the difference between the sampling frequency and the rotation frequency is small, the low-pass filtering calculation in step S450 can be omitted. However, if a vibration acceleration sensor is used to acquire the vibration signal in step S440, since the sampling frequency is high and the difference between the sampling frequency and the rotation frequency is large, the sampled signal may include other and more noise signals. In this case, a low-pass filtering method can be used to remove the acquired high-frequency signals and improve the accuracy of the vibration signals in the training and test data sets.

[0128] S460, calculating the actual rotation speed.

[0129] It is understandable that the actual rotation speed of each set of vibration signals in the training dataset and the test dataset can be calculated based on the data in the training dataset and the test dataset of the vibration signals output in step S440 or step S450.

[0130] For example, FIG5D shows a time domain diagram of a vibration signal acquired using a vibration velocity sensor. The acquisition time of this vibration signal is 2 seconds. Based on the time domain diagram of the vibration signal shown in FIG5D, a Fourier transform or other method can be used to obtain the frequency spectrum of the vibration signal shown in FIG5E. The frequency range of this vibration signal is [0, 50] Hz. Based on the frequency spectrum of the vibration signal shown in FIG5E, the actual speed fluctuation range of the asynchronous motor in step S420 is [0, v0], that is, [0, 15] Hz. The maximum value can be obtained within the actual speed fluctuation range of the asynchronous motor, that is, the actual speed v1 of the asynchronous motor corresponding to the vibration signal in FIG5D = 13.3 Hz. Then, based on the theoretical speed and actual speed of the asynchronous motor, a comparison diagram of the theoretical speed and actual speed of the asynchronous motor shown in FIG5F can be obtained. It can be understood that the actual speed of the asynchronous motor is less than the theoretical speed.

[0131] S470: Calculate the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio.

[0132] It can be understood that the equivalent slip, equivalent speed ratio and equivalent acceleration ratio of the current signal and vibration signal corresponding to each group in the training data set and the test data set can be calculated respectively based on the actual speed in step S460 and the theoretical speed in step S420.

[0133] In the first case, the asynchronous motor is in a steady state, that is, the theoretical speed and actual speed of the asynchronous motor are constant. According to the equivalent slip equal to the difference between the actual speed and the theoretical speed, the equivalent slip corresponding to the theoretical speed v0 is ε v=1.70Hz.

[0134] According to the equivalent speed ratio of the asynchronous motor, it is equal to the ratio between the actual speed of the asynchronous motor and the theoretical speed sent by the controller of the asynchronous motor. It can be obtained that the equivalent speed ratio r of the asynchronous motor is v =v1 / v0=88.67%.

[0135] In the second case, the asynchronous motor outputs a non-steady speed, that is, the actual speed of the asynchronous motor changes, for example, the change in the actual speed per unit time is greater than or equal to the first threshold.

[0136] For example, Figure 5G shows a time-domain schematic diagram of another set of current signals, which were collected over a 4-second period. Based on Figure 5G , the time-frequency schematic diagram of the asynchronous motor in Figure 5H can be obtained using the Fourier transform method. Figure 5I shows a time-domain schematic diagram of another set of vibration signals, which were collected over a 4-second period. Based on Figure 5I , the time-frequency schematic diagram of the asynchronous motor in Figure 5J can be obtained using the Fourier transform method.

[0137] According to Figure 5H, the theoretical speed v0 of the asynchronous motor and its average value can be obtained The average value of the theoretical speed According to Figure 5J, the actual speed v1 of the motor can be obtained. By performing first-order difference calculations on the theoretical speed v0 and actual speed v1 of the asynchronous motor, the theoretical acceleration a0 and actual acceleration a1 of the asynchronous motor can be obtained, where the theoretical acceleration a0 = v0 / Δt and the actual acceleration a1 = v1 / Δt, where t is the sampling time of the current signal in Figure 5G and the vibration signal in Figure 5I. Then, the equivalent acceleration ratio r of the asynchronous motor can be obtained based on the ratio between the actual acceleration of the asynchronous motor and the theoretical acceleration sent by the controller of the asynchronous motor. a =a1 / a0.

[0138] S480: Calculate the mean square value of the vibration signal and use the mean square value as the torque.

[0139] In a possible implementation, the torque may be obtained by acquiring a torque signal z(t) collected by a torque sensor, where t is a sampling duration.

[0140] In another possible implementation, the torque may be obtained by calculating the mean square value of the vibration signal of the asynchronous motor.

[0141] S490, calculating the distribution proportions of the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio of the data of the training data set in each distribution area within a preset confidence range.

[0142] In one possible implementation, the data of equivalent slip, equivalent speed ratio and equivalent acceleration ratio of the training data set and the test data set of the asynchronous motor can be divided into several distribution areas according to the gear position, torque, theoretical speed in a steady state, and the average value of theoretical speed in an unsteady state of the asynchronous motor. For example, each distribution area of ​​the equivalent slip of the training data set of the asynchronous motor has the same theoretical speed or the average value of the theoretical speed, the same gear position and the same torque. Alternatively, each distribution area of ​​the equivalent slip of the training data set of the asynchronous motor has the same theoretical speed or the average value of the theoretical speed, and the same torque. Alternatively, each distribution area of ​​the equivalent slip of the training data set of the asynchronous motor has the same gear position and the same torque.

[0143] It can be understood that the principle for dividing the distribution areas is based on dividing the data of the three characteristic parameters of equivalent slip, equivalent speed ratio, and equivalent acceleration ratio in the training and test datasets of the asynchronous motor according to the same operating scenario. The same distribution area is also the same operating scenario. Therefore, the operating status of the asynchronous motor can be evaluated in the same operating scenario. In the embodiments of this application, the principle for dividing the distribution areas of the asynchronous motor is not specifically limited.

[0144] In a possible implementation, if the distribution area is divided according to the same theoretical speed or the average value of the theoretical speed, the same gear and the same torque, assuming that the torque of the asynchronous motor is z(t), the gear is i, and i is a natural number, the torque parameter can be recorded as z i , a set of torque z within the sampling time i =mean(z(t)), where mean(·) represents the averaging operation.

[0145] Then, in a steady state, the theoretical speed is v0 and the torque is z i In the distribution area, the equivalent slip of the asynchronous motor corresponding to the current signal in FIG5A and the vibration signal in FIG5D can be expressed as The equivalent speed ratio of the asynchronous motor is The equivalent acceleration ratio of the asynchronous motor is

[0146] In the unsteady state, the average value of the theoretical speed is v0 and the torque is z i In the distribution area, the equivalent speedup ratio of the asynchronous motor corresponding to the current signal in Figure 5G and the vibration signal in Figure 5I is

[0147] It can be understood that the distribution center of each distribution area can be obtained according to the respective distribution areas of the equivalent slip, the equivalent speed ratio and the equivalent acceleration ratio.

[0148] For example, the distribution center of the equivalent deviation distribution area of ​​the training data set can be expressed as The distribution center of the distribution area of ​​the equivalent speed ratio of the training data set can be expressed as The distribution center of the distribution area of ​​the equivalent speedup ratio of the training data set can be expressed as k represents the sequence number of the distribution area, and k is a natural number.

[0149] Since the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio conform to a normal distribution, a preset confidence interval can be set to any one of the following: [-3σ, 3σ], [-2σ, 2σ], or [-σ, σ], where σ is the standard deviation of each characteristic parameter, such as the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio. Statistics can be collected for the data in each distribution area of ​​the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio of the training data set, along with the distance from the center of each distribution area, the number of samples within the preset confidence interval, and the distribution ratio of the total number of samples in each distribution area.

[0150] Among them, the data in each distribution area of ​​the equivalent deviation of the data in the training data set, the distance from the distribution center of each distribution area, the number of samples within the preset confidence range, and the distribution ratio of the total number of samples can be expressed as The data in each distribution area of ​​the equivalent speed ratio of the data in the training data set, the distance from the distribution center of each distribution area, the number of samples within the preset confidence range, and the distribution ratio of the total number of samples can be expressed as The data in each distribution area of ​​the equivalent speedup ratio of the data in the training data set, the distance from the distribution center of each distribution area, the number of samples within the preset confidence range, and the distribution ratio of the total number of samples can be expressed as

[0151] S500: Calculate the equivalent slip, equivalent speed ratio, and equivalent acceleration ratio of the test data set in each distribution area, and their respective distribution proportions within a preset confidence range.

[0152] It is understood that a similar method to step S490 can be used, and the distribution center of the distribution area of ​​the equivalent slip of the data of the test data set can be expressed as The distribution center of the equivalent speed ratio distribution area of ​​the test data set can be expressed as The distribution center of the equivalent speedup ratio of the test data set can be expressed as k represents the serial number of the distribution center, and k is a natural number.

[0153] In addition, the same preset confidence range as the training data set can be obtained to calculate the data in each distribution area of ​​the equivalent deviation of the data in the test data set, the distance from the distribution center of each distribution area, the number of samples in the preset confidence range, and the distribution ratio of the total number of samples in each distribution area. The data in each distribution area of ​​the equivalent speed ratio of the test data set, the distance from the distribution center of each distribution area, the number of samples within the preset confidence range, and the distribution ratio of the total number of data samples in each distribution area The data in each distribution area of ​​the equivalent speedup ratio of the test data set, the distance from the distribution center of each distribution area, the number of samples within the preset confidence range, and the distribution ratio of the total number of data samples in each distribution area

[0154] S510, calculating the health level corresponding to the test data set.

[0155] Specifically, the distribution difference of the equivalent slip between the training dataset and the test dataset in each distribution area, that is, the distance between the two distribution centers, can be calculated based on the results in step S490 and step S500. The distribution difference of the equivalent speed ratio of the training data set and the test data set in each distribution area, that is, the distance between the two distribution centers And the distribution difference of the equivalent speedup ratio of the training data set and the test data set in each distribution area, that is, the distance between the two distribution centers

[0156] Then, the statistical difference of the equivalent slip between the training dataset and the test dataset in all distribution areas, the statistical difference of the equivalent speed ratio between the training dataset and the test dataset in all distribution areas, and the statistical difference of the equivalent acceleration ratio between the training dataset and the test dataset in all distribution areas are calculated.

[0157] Among them, the statistical difference of the equivalent shift between the training dataset and the test dataset in all distribution areas is:

[0158] The statistical difference of the equivalent speed ratio between the training dataset and the test dataset in all distribution areas is:

[0159] The statistical difference of the equivalent speedup ratio of the training dataset and the test dataset in all distribution areas is:

[0160] Then, the above results are substituted into the health formula to obtain the health of the asynchronous motor corresponding to the test data set.

[0161] Among them, health is expressed as score, ω v With ω a is the weight coefficient of equivalent speed ratio and equivalent acceleration ratio, ω v +ω a =1. You can adjust ω according to the actual usage. v ,ω a , for example, setting ω v =ω a =0.5.ω k is the weight coefficient of equivalent slip, generally, You can also adjust according to the actual situation Need to meet In the embodiment of the present application, for the specific values ​​of the weight coefficients of the equivalent speed ratio and the equivalent acceleration ratio, for λ k The specific value of is not limited.

[0162] It is understood that the asynchronous motor can be evaluated as being in good health when the health level is greater than or equal to 0.85; as being in good health when the health level is less than 85 and greater than or equal to 0.60; and as being in poor health, indicating a fault and requiring repair, when the health level is less than 60. In the embodiments of the present application, the aforementioned settings are not specifically limited.

[0163] S520 , a file is created based on the distribution area, equivalent slip, equivalent speed ratio, equivalent acceleration ratio, and health.

[0164] In the above health assessment method, characteristic parameters corresponding to the training data set and the test data set for characterizing the speed state of the asynchronous motor are calculated respectively. For example, the characteristic parameters may include equivalent slip, equivalent speed ratio and equivalent acceleration ratio. Then, the characteristic parameters of the training data set and the test data set in each distribution area are compared to obtain the distribution difference of the characteristic parameters of the training data set and the test data set in each distribution area, as well as the statistical difference of the characteristic parameters of the training data set and the test data set in all distribution areas. Finally, based on the statistical difference of the characteristic parameters of the training data set and the test data set in all distribution areas, and the weight of each characteristic parameter, the specific value of the health of the asynchronous motor corresponding to the test data set is obtained.

[0165] It is understandable that any type of failure in an asynchronous motor may directly cause a change in the output state of the asynchronous motor, thereby affecting the normal use of the asynchronous motor. Therefore, the above-mentioned health assessment method can more accurately assess the health of the asynchronous motor's immediate operating state by comparing the characteristic parameters of the output state of the asynchronous motor in a healthy operating state corresponding to the training data set with the characteristic parameters of the output state of the asynchronous motor in the immediate operating state corresponding to the test data set. In addition, by comparing the characteristic parameters of the asynchronous motor's speed, a more accurate comparison result between the asynchronous motor's immediate health state and healthy operating state can be obtained even when the application scenario is not comprehensive or the amount of data is insufficient.

[0166] Moreover, by dividing the above parameters into different files for storage, an accurate and rich reference basis is provided for subsequent life prediction and degradation prediction of the asynchronous motor.

[0167] It is understood that the electronic device 100 may include but is not limited to user equipment (UE), a terminal, etc. For example, the electronic device may be a tablet computer (portable Android device, PAD), a personal digital assistant (PDA), a handheld device with wireless communication function, a computing device, a vehicle-mounted device or a wearable device, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control (industrial control), a wireless terminal in self-driving (self-driving), a wireless terminal in remote medical (remote medical), a wireless terminal in smart grid (smart grid), a wireless terminal in transportation safety (transportation safety), a wireless terminal in smart city (smart city), a wireless terminal in smart home (smart home), and other mobile terminals or fixed terminals. In the embodiments of the present application, the form of the terminal device is not specifically limited.

[0168] The hardware structure of the electronic device 100 in the embodiment of the present application is described below with reference to FIG. 6 .

[0169] FIG6 shows a schematic diagram of the hardware structure of an electronic device 100 according to some embodiments of the present application. As shown in FIG6 , the electronic device 100 includes one or more processors 101, a system memory 102, a non-volatile memory (NVM) 103, a communication interface 104, an input / output (I / O) device 105, and a system control logic 106 for coupling the processor 101, the system memory 102, the non-volatile memory 103, the communication interface 104, and the input / output (I / O) device 105.

[0170] Wherein: the processor 101 may include one or more processing units, for example, a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a digital signal processor (DSP), a neural network processor (NPU), a microprocessor (micro-programmed control unit, MCU), a baseband processor, an artificial intelligence (AI) processor or a processing module or processing circuit of a programmable logic device (field programmable gate array, FPGA) or other image processing device including the present application, a processor that implements the above-mentioned image processing method, wherein different processing units can be independent devices or integrated into one or more processors. The specific processor type is not specifically required here. The processor 101 can be used to execute the health assessment method of the embodiment of the present application.

[0171] The system memory 102 is a volatile memory, such as random-access memory (RAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc. The system memory is used to temporarily store data and / or instructions.

[0172] The non-volatile memory 103 may include one or more tangible, non-transitory computer-readable media for storing data and / or instructions. In some embodiments, the non-volatile memory 103 may include any suitable non-volatile memory such as flash memory and / or any suitable non-volatile storage device, such as a hard disk drive (HDD), a compact disc (CD), a digital versatile disc (DVD), a solid-state drive (SSD), etc. In some embodiments, the non-volatile memory 103 may also be a removable storage medium, such as a secure digital (SD) memory card.

[0173] In particular, the system memory 102 and the non-volatile memory 103 may respectively include a temporary copy and a permanent copy of the instruction 107. The instruction 107 may include instructions executed by at least one of the processors 101 to enable the electronic device 100 to implement the model detection method provided in various embodiments of the present application.

[0174] In some embodiments, the processor 101 can call and execute the execution instructions of the model detection provided by each embodiment of the present application stored in the system memory 102 and the non-volatile memory 103 to implement the health assessment method provided by the embodiment of the present application.

[0175] The communication interface 104 may include a transceiver for providing a wired or wireless communication interface for the electronic device 100, thereby communicating with any other suitable device via one or more networks. In some embodiments, the communication interface 104 may be integrated into other components of the electronic device 100, for example, the communication interface 104 may be integrated into the processor 101. In some embodiments, the electronic device 100 can communicate with other devices via the communication interface 104.

[0176] The communication interface 104 may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0177] The MIPI interface can be used to connect the processor 101 to peripheral devices such as a display screen and a camera. MIPI interfaces include the camera serial interface (CSI) and the display serial interface (DSI). In some embodiments, the processor 101 and the camera communicate via the CSI interface to enable the camera function of the electronic device 100. The processor 101 and the display communicate via the DSI interface to enable the display function of the electronic device 100.

[0178] The GPIO interface can be configured through software. The GPIO interface can be configured as a control signal or a data signal. In some embodiments, the GPIO interface can be used to connect the processor 110 to a camera, display, wireless communication module, audio module, sensor module, etc. The GPIO interface can also be configured as an I2C interface, an I2S interface, a UART interface, a MIPI interface, etc.

[0179] A USB interface is an interface that complies with USB standards and specifications, and may be a Mini USB interface, a Micro USB interface, a USB Type-C interface, or the like. A USB interface can be used to connect a charger to charge the electronic device 100, or to transfer data between the electronic device 100 and peripheral devices. This interface can also be used to connect other electronic devices.

[0180] It is understood that the interface connection relationship between the modules illustrated in the embodiments of the present application is merely an illustrative description and does not constitute a structural limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may also adopt different interface connection methods in the above embodiments, or a combination of various interface connection methods.

[0181] The input / output (I / O) device 105 may include input devices such as a keyboard, a mouse, etc., and output devices such as a display, etc. A user may interact with the electronic device 100 through the input / output (I / O) device 105 .

[0182] System control logic 106 may include any suitable interface controller to provide any suitable interface with other modules of terminal 100. For example, in some embodiments, system control logic 106 may include one or more memory controllers to provide interfaces to system memory 102 and non-volatile memory 103.

[0183] In some embodiments, at least one of the processors 101 may be packaged together with the logic of one or more controllers for the system control logic 106 to form a system in package (SiP). In other embodiments, at least one of the processors 101 may be integrated with the logic of one or more controllers for the system control logic 106 on the same chip to form a system-on-chip (SoC). The system control logic 106 may generate operation control signals based on instruction opcodes and timing signals to control instruction fetching and execution.

[0184] Although not shown in FIG. 6 , the electronic device 100 may further include a Bluetooth device, an external memory interface for connecting to an external memory card, a near field communication (NFC) device, etc., which are not described in detail here.

[0185] It will be understood that the structure of the electronic device 100 shown in FIG6 is merely an example. In other embodiments, the electronic device 100 may include more or fewer components than shown, or may combine or separate certain components, or may have different component arrangements. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0186] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0187] It will be apparent to those skilled in the art that some of the specific details presented above regarding the electronic device 100 may not be necessary for practicing a particular embodiment or its equivalent. Similarly, other electronic devices may include a greater number of subsystems, modules, components, etc. Where appropriate, some submodules may be implemented as software or hardware. Therefore, it should be understood that the above description is not intended to be exhaustive or to limit the present disclosure to the precise form described herein. On the contrary, it will be apparent to those skilled in the art that many modifications and variations are possible based on the above teachings.

[0188] The various embodiments disclosed in this application can be implemented in hardware, software, firmware, or a combination of these implementation methods. The embodiments of the present application can be implemented as a computer program or program code executed on a programmable system, which includes at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0189] Program code can be applied to input instructions to perform the functions described herein and generate output information. The output information can be applied to one or more output devices in a known manner. For purposes of this application, a processing system includes any system having a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application specific integrated circuit (ASIC), or a microprocessor.

[0190] Program code can be implemented with a high-level programming language or an object-oriented programming language to communicate with the processing system. Where necessary, program code can also be implemented in assembly language or machine language. In fact, the mechanism described in this application is not limited to the scope of any particular programming language. In either case, the language can be a compiled language or an interpreted language.

[0191] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried or stored on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, instructions may be distributed over a network or through other computer-readable media. Therefore, a machine-readable medium may include any mechanism for storing or transmitting information in a machine (e.g., computer) readable form, including but not limited to a floppy disk, an optical disk, an optical disk, a magneto-optical disk, a read-only memory (ROM), a random access memory (RAM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic card or an optical card, a flash memory, or a tangible machine-readable memory for transmitting information (e.g., a carrier wave, an infrared signal, a digital signal, etc.) using the Internet in an electrical, optical, acoustic, or other form of propagation signal. Accordingly, machine-readable media includes any type of machine-readable media suitable for storing or transmitting electronic instructions or information in a form readable by a machine (eg, a computer).

[0192] In the accompanying drawings, some structural or method features may be shown in a particular arrangement and / or order. However, it should be understood that such a particular arrangement and / or order may not be required. Rather, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. In addition, the inclusion of a structural or method feature in a particular figure does not imply that such feature is required in all embodiments, and in some embodiments, such features may not be included or may be combined with other features.

[0193] It should be noted that the units / modules mentioned in the various device embodiments of the present application are all logical units / modules. Physically, a logical unit / module can be a physical unit / module, or a part of a physical unit / module, or can be implemented as a combination of multiple physical units / modules. The physical implementation of these logical units / modules themselves is not the most important. The combination of functions implemented by these logical units / modules is the key to solving the technical problems raised by this application. In addition, in order to highlight the innovative part of this application, the above-mentioned device embodiments of this application do not introduce units / modules that are not closely related to solving the technical problems raised by this application. This does not mean that other units / modules do not exist in the above-mentioned device embodiments.

[0194] It should be noted that, in the examples and description of the present application, relational terms such as first and second, etc., are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a" does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0195] While the present application has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the scope of the present application.

Claims

1. A health assessment method, applied to electronic equipment, characterized in that: include: Acquire a first speed characteristic parameter of the motor within a first time period; The health of the motor during the first time period is determined according to a difference between the first speed characteristic parameter and a standard speed characteristic parameter.

2. The method according to claim 1, characterized in that The first speed characteristic parameters include the equivalent slip within the first time length, the equivalent speed ratio within the first time length, and the equivalent acceleration ratio within the first time length; the standard speed characteristic parameters include the equivalent slip within the second time length, the equivalent speed ratio within the second time length, and the equivalent acceleration ratio within the second time length, and the second time length is any period of time that the motor is in a healthy operating state.

3. The method according to claim 2, characterized in that The equivalent slip is determined based on the difference between the actual speed of the motor and the theoretical speed of the motor in the first case; The equivalent speed ratio is determined based on the ratio between the actual speed of the motor and the theoretical speed of the motor in the first case; The equivalent acceleration ratio is determined based on the ratio between the actual acceleration of the motor and the theoretical acceleration sent by the controller of the motor in the second case; The first situation includes a situation where the theoretical speed of the motor and the actual speed of the motor are constant values, and the second situation includes a situation where the theoretical speed of the motor and the actual speed of the motor are not constant values.

4. The method according to claim 1, characterized in that The determining the health of the motor during the first time period according to the difference between the first speed characteristic parameter and the standard speed characteristic parameter includes: Obtaining a distribution difference between the first speed characteristic parameter and the standard speed characteristic parameter in each working scene; Obtaining data of a first speed characteristic parameter in each working scene within a first confidence range, and a distribution ratio of the data of the first speed characteristic parameter in all working scenes; Obtaining the health of the motor during the first duration according to the distribution difference and the distribution proportion; Among them, each of the working scenes is a scene of the same working condition.

5. The method according to claim 4, characterized in that The same working condition includes: have the same theoretical speed or the same average value of the theoretical speed, the same gear and the same torque; or have the same theoretical speed or the same average value of the theoretical speed, and the same torque; or Same gears and same torque.

6. The method according to claim 4, characterized in that The obtaining of the distribution difference between the first speed characteristic parameter and the standard speed characteristic parameter in each working scene includes: Obtaining, in each working scenario, a distribution center of an equivalent slip within the first time period, a distribution center of an equivalent speed ratio within the first time period, and a distribution center of an equivalent acceleration ratio within the first time period corresponding to the first speed characteristic parameter; Obtaining, in each working scenario, a distribution center of an equivalent slip within a second time length, a distribution center of an equivalent speed ratio within the second time length, and a distribution center of an equivalent acceleration ratio within the second time length corresponding to the standard speed characteristic parameter; Obtaining, in each working scene, a first distance between a distribution center of the equivalent slip within the first duration and a distribution center of the equivalent slip within the second duration; Obtaining, in each working scene, a second distance between a distribution center of the equivalent speed ratio within the first time length and a distribution center of the equivalent speed ratio within the second time length; Obtain, in each working scene, a third distance between a distribution center of the equivalent speedup ratio within the first duration and a distribution center of the equivalent speedup ratio within the second duration.

7. The method according to claim 6, characterized in that The obtaining of the data of the first speed characteristic parameter in each working scene within the first confidence range and the distribution ratio of the data of the first speed characteristic parameter in all working scenes includes: Obtaining, in each working scene, data of equivalent slip within the first duration, the distance from the distribution center of each working scene, the number of samples within the first confidence range, and a first proportion of the total number of samples of equivalent slip data within the first duration in each working scene; Obtaining data of the equivalent speed ratio within the first duration in each working scene, the distance from the distribution center of each working scene, the number of samples within the first confidence range, and the second proportion of the total number of samples of the equivalent speed ratio within the first duration in each working scene; Obtain the data of the equivalent acceleration ratio within the first time length in each work scene, the distance from the distribution center of each work scene, the number of samples within the first confidence range, and the third proportion of the total number of samples of the data of the equivalent acceleration ratio within the first time length in each work scene.

8. The method according to claim 7, characterized in that The obtaining the health of the motor in the first time period according to the distribution difference and the distribution proportion includes: According to the first distance and the first proportion in each working scene, obtain a first statistical difference between an equivalent slip within a first duration and an equivalent slip within a second duration of all working scenes; According to the second distance and the second proportion in each working scene, obtain a second statistical difference between the equivalent speed ratio within the first duration and the equivalent speed ratio within the second duration of all working scenes; Obtain, according to the third distance and the third proportion in each work scene, a third statistical difference between the equivalent acceleration ratio within the first duration and the equivalent acceleration ratio within the second duration of all work scenes; The health of the motor in the first duration is obtained based on the first statistical difference, the second statistical difference, the third statistical difference, and the weight coefficients corresponding to the equivalent slip, the weight coefficients corresponding to the equivalent speed ratio, and the weight coefficients corresponding to the equivalent acceleration ratio.

9. The method according to claim 4, characterized in that The first confidence range includes: any one of: [-3σ, 3σ] range, [-2σ, 2σ] range, [-σ, σ] range, wherein σ is the standard deviation of each parameter in the first rotation speed characteristic parameter.

10. A computer-readable storage medium, characterized in that: The readable storage medium stores instructions, which, when executed on an electronic device, enable the electronic device to implement the method according to any one of claims 1 to 9.

11. An electronic device, characterized in that: include: a memory for storing instructions to be executed by one or more processors of the electronic device; And a processor, which is one of the processors of the electronic device, configured to execute instructions stored in the memory to implement the method according to any one of claims 1 to 9.

Images