CN111819452A

CN111819452A - Method and device for acquiring running state of motor

Info

Publication number: CN111819452A
Application number: CN201980005478.4A
Authority: CN
Inventors: 李延召
Original assignee: SZ DJI Technology Co Ltd
Current assignee: SZ DJI Technology Co Ltd
Priority date: 2019-02-02
Filing date: 2019-02-02
Publication date: 2020-10-23
Also published as: WO2020155147A1

Abstract

A method and a device for acquiring the running state of a motor are provided, the method comprises the following steps: acquiring a signal related to an operation state of a motor (S101); characteristic information of the signal is acquired, and an operation state of the motor is acquired based on the characteristic information (S102). The method and the device for acquiring the running state of the motor can efficiently and accurately acquire the running state of the motor.

Description

Method and device for acquiring running state of motor

Technical Field

The present disclosure relates to computer technologies, and in particular, to a method and an apparatus for acquiring a running state of a motor.

Background

Monitoring the running state of the motor is an important factor for ensuring that the equipment driven by the motor can run reliably and stably.

At present, a method for monitoring the running state of a motor is generally judged in a mode of listening by human ears, namely, the human ears judge the running state of the motor by listening to noise in the running process of the motor. The user can stand near the motor to listen to the noise in the motor running process, and the noise in the motor running process can be recorded into an audio file to be listened off line.

However, the running state of the motor is judged in a mode of listening by human ears, so that the judgment is not accurate enough and the efficiency is low.

Disclosure of Invention

The embodiment of the application provides a method and a device for acquiring the running state of a motor, which can efficiently and accurately acquire the running state of the motor.

In a first aspect, an embodiment of the present application provides a method for acquiring a running state of a motor, including:

acquiring a signal related to the running state of the motor;

and acquiring the characteristic information of the signal, and acquiring the running state of the motor according to the characteristic information.

In a second aspect, an embodiment of the present application provides an apparatus for acquiring an operating state of a motor, including: a memory, a processor, and a communication bus through which the memory and the processor are connected;

a memory for storing a computer program;

a processor for invoking the computer program to perform the following operations:

acquiring a signal related to the running state of the motor;

In a third aspect, embodiments of the present application provide a computer-readable storage medium comprising a program or instructions for performing the method of the first aspect and possible designs when the program or instructions are run on a computer.

In a fourth aspect, an embodiment of the present application provides an electronic device, which includes a motor and a device for acquiring an operation state of the motor, where the device is configured to acquire the operation state of the motor.

According to the method, the running state of the motor is obtained by obtaining the characteristic information of the signal related to the running state of the motor, the running state of the motor is judged in a mode of listening to sound of human ears, and the running state of the motor can be objectively reflected by the characteristic information of the signal related to the running state of the motor, so that the method for obtaining the running state of the motor is high in efficiency and accuracy.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.

Fig. 1 is a first flowchart of a method for acquiring an operating state of a motor according to an embodiment of the present disclosure;

FIG. 2 is a diagram of a noise signal of a motor provided in an embodiment of the present application;

fig. 3 is a second flowchart of a method for acquiring an operating state of a motor according to an embodiment of the present application;

FIG. 4 is a schematic diagram of triangular window down-sampling according to an embodiment of the present disclosure;

fig. 5 is a third flowchart of a method for acquiring an operating state of a motor according to an embodiment of the present application;

FIG. 6 is a diagram of N segments of the signals of FIG. 2;

fig. 7 is a first schematic structural diagram of an apparatus for acquiring an operating state of a motor according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a second device for acquiring an operating state of a motor according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Specifically, in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone, wherein A and B can be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of the singular or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or multiple. The terms "first," "second," and the like in this application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. The "value between x and y" in the present embodiment includes both the values of x and y in addition to the value in the interval (x, y).

The embodiment of the application provides a method for efficiently and accurately acquiring the running state of a motor.

The following describes a method for acquiring a motor operating state according to an embodiment of the present application with reference to a specific embodiment.

Fig. 1 is a first flowchart of a method for acquiring an operating state of a motor according to an embodiment of the present application. The executing body of the embodiment may be a device for acquiring the running state of the motor, and the device for acquiring the running state of the motor may be implemented by hardware or software. The method of the embodiment comprises the following steps:

step S101, acquiring a signal related to the running state of a motor;

specifically, during operation of the motor, a signal related to an operating state of the motor is acquired. The signal related to the operational state of the electric machine is one or more of: the noise signal of the motor, the current signal of the motor, the signal that the inertial measurement unit setting on the motor outer wall measured. Wherein, the noise signal of the motor can be collected by a microphone, an accelerometer, a vibration sensor, a piezoelectric crystal and/or a barometer; the current signal of the motor can be measured by an ammeter; the signal of the inertial measurement unit may be, for example, a vibration signal or a current signal. It is understood that the signal related to the operation state of the motor may be other signals that can reflect the operation state of the motor, and this embodiment is only an exemplary illustration.

The motor in this embodiment may be a motor that is not assembled to the device, and may also be a motor that has been assembled to the device, and the device that is assembled with the motor may be any electronic device that needs to be driven by the motor, such as a radar, an unmanned aerial vehicle, an electric fan system, and the like, where the radar may be a mechanical scanning type laser radar, and the unmanned aerial vehicle may be an unmanned aerial vehicle, an unmanned ship, and the like, and is not limited herein.

Fig. 2 is a noise signal diagram of a motor according to an embodiment of the present disclosure. As shown in fig. 2, the noise signal in fig. 2 is an original noise signal, i.e., a noise signal in the time domain.

And S102, acquiring characteristic information of the signal, and acquiring the running state of the motor according to the characteristic information.

Specifically, after the signal related to the operation state of the motor is acquired, the signal related to the operation state of the motor may be processed to obtain the characteristic information of the signal related to the operation state of the motor. The signals related to the running state of the motor can be directly processed to obtain the characteristic information of the signals related to the running state of the motor, and partial signals can be extracted from the signals related to the running state of the motor to be processed to obtain the characteristic information of the signals related to the running state of the motor.

It is understood that, in the case of directly processing the signal related to the operation state of the motor, the signal related to the operation state of the motor may be a collected signal related to the operation state of the motor, or may be a signal extracted from the collected signal related to the operation state of the motor. In the case where a part of the signals related to the operation state of the motor is extracted from the signals related to the operation state of the motor for processing, the signals related to the operation state of the motor may be collected signals related to the operation state of the motor.

Wherein the characteristic information of the signal related to the operation state of the motor may be at least one of: intensity information, distribution information. In other embodiments, the characteristic information of the signal related to the operation state of the motor may be other information, such as power information, and is not limited herein. The intensity information may be obtained according to a signal related to the operating state of the motor in a time domain, and may also be obtained according to a signal related to the operating state of the motor in a frequency domain, where the signal related to the operating state of the motor in the frequency domain may be a magnitude spectrum corresponding to the signal related to the operating state of the motor. The distribution information may be acquired from a distribution signal corresponding to a signal related to the operation state of the motor, and the distribution signal may be a cepstrum signal corresponding to the signal related to the operation state of the motor. In other embodiments, the distribution signal corresponding to the signal relating to the operating state of the electric machine in the time domain may also be obtained according to other suitable algorithms.

In one mode, the signal relating to the operating state of the motor is preprocessed before the characteristic information of the signal relating to the operating state of the motor is acquired. The preprocessing of the signal related to the operation state of the motor may include performing normalization processing on the signal related to the operation state of the motor or a signal extracted from the signal related to the operation state of the motor to obtain a normalized signal. At this time, characteristic information of the signal related to the operation state of the motor may be acquired from the normalized signal.

The characteristic information of the signal related to the running state of the motor is acquired, so that the running state of the motor can be reflected by the characteristic information, and the running state of the motor can be acquired according to the characteristic information after the characteristic information is acquired.

It is understood that the motor may have at least one operation state, and the acquired characteristic information of the signal related to the operation state of the motor may be different, and the operation state of the corresponding motor may be different.

The operating state of the motor corresponding to the preset characteristic information can be obtained according to the corresponding relation between the preset characteristic information and the operating state of the motor, and the operating state of the motor corresponding to the characteristic information can be obtained according to a machine learning algorithm.

Specifically, in one embodiment: the method for acquiring the characteristic information of the signal related to the running state of the motor and acquiring the running state of the motor according to the characteristic information comprises the following steps: the method comprises the steps of obtaining characteristic information of a signal related to the running state of the motor, and obtaining the running state of the motor corresponding to the characteristic information according to the characteristic information and a preset corresponding relation, wherein the preset corresponding relation comprises multiple preset characteristic information and the running state corresponding to each preset information.

Wherein, according to this characteristic information, obtain the running state of this motor that corresponds with this characteristic information according to presetting the corresponding relation, include: determining target preset characteristic information corresponding to the characteristic information; and determining the running state corresponding to the target preset characteristic information in the preset corresponding relation as the running state of the motor.

For example, the motor may have the following operating states, but is not limited to the following:

(1) the motor starts abnormally.

In this case, the characteristic information of the signal relating to the operating state of the electric machine corresponds to a low overall intensity of the signal, for example, a lower overall intensity of the signal than a predefined intensity value.

(2) After the first period of time, the motor runs abnormally.

At this time, the characteristic information of the signal related to the operation state of the motor corresponds to the total intensity of the signal being moderate, for example, the total intensity of the signal is within a normal range, but the intensity of the signal is relatively large at some frequencies, for example, the intensity of the signal is out of the normal range at some frequencies.

(3) The motor operates normally;

in this case, the characteristic information of the signal relating to the operating state of the electric machine corresponds to a moderate overall intensity of the signal, for example, the overall intensity of the signal is within a normal range, while the intensity of the signal at each frequency is largely or entirely within the normal range.

(4) The motor runs abnormally after the second time length; wherein the first duration is less than the second duration;

at this time, the characteristic information of the signal related to the operation state of the motor corresponds to the total intensity of the signal being moderate, for example, the total intensity of the signal is within a normal range, but the intensity of the signal is slightly larger at a plurality of frequencies, for example, the intensity of the signal is slightly out of the normal range at a plurality of frequencies.

(5) The noise during the operation of the motor is too great.

At this time, the characteristic information of the signal related to the operation state of the motor corresponds to a large total intensity of the signal, for example, out of a normal range.

In another embodiment, a machine learning method may be used to obtain the operating state of the motor corresponding to the characteristic information according to the characteristic information. The operation state of the motor acquired by this embodiment may also be any one of the states (1) to (5) in the above examples.

Specifically, in the case of using a machine learning method to acquire the operating state of the motor corresponding to the characteristic information from the characteristic information:

according to the characteristic information, acquiring the running state of the motor corresponding to the characteristic information, wherein the running state comprises the following steps: and acquiring the running state of the motor corresponding to the characteristic information by adopting a machine learning algorithm according to the characteristic information and a machine learning model. The machine learning model is obtained by adopting the machine learning algorithm and training based on a plurality of training samples and labels of the training samples, the training samples comprise characteristic information of signals related to the running state of the first motor, and the labels of the training samples are used for indicating the running state of the first motor.

Specifically, the characteristic information obtained in the step is used as an input of a machine learning model, and a target label is output after calculation by adopting a machine learning algorithm, wherein the target label is used for indicating the running state of the motor.

It is understood that the first motor may be the motor in this embodiment, and may be other motors. The feature information of the signal relating to the operation state of the first motor in the training sample includes the same kind of feature as the feature information of the signal relating to the operation state of the motor obtained in this step. The label of the training sample may be a string indicating the operating state of the first motor, and accordingly, the target label is a string indicating the operating state of the motor in this implementation.

And when the machine learning algorithm is a neural network algorithm, the machine learning model is a neural network model. The neural network algorithm may be any one of the following: a Back Propagation (BP) Neural Network, a Stack Automatic Encoder (SAE) Neural Network, a Long Short Term Memory Network (LSTM) Neural Network, a Recurrent Neural Network (RNN) Neural Network, and a convolutional Neural Network.

In the embodiment, the running state of the motor is obtained by obtaining the characteristic information of the signal related to the running state of the motor, the running state of the motor is judged without hearing by human ears, and the running state of the motor can be objectively reflected by the characteristic information of the signal related to the running state of the motor, so that the efficiency and the accuracy of obtaining the running state of the motor by the method are high.

A specific implementation of the above embodiment follows when the characteristic information of the signal relating to the operating state of the electric machine comprises intensity information and/or distribution information. Fig. 3 is a second flowchart of a method for acquiring an operating state of a motor according to an embodiment of the present application. Referring to fig. 3, the method of the present embodiment includes:

step S201, acquiring a signal related to the operation state of the motor.

Specifically, the specific implementation of this step refers to step S101 in the above embodiment, and is not described here again.

Step S202, intensity information and/or distribution information of signals related to the running state of the motor are acquired.

Specifically, acquiring strength information and/or distribution information of a signal related to an operation state of the motor includes:

a1, acquiring a normalized amplitude spectrum corresponding to the signal related to the running state of the motor.

Specifically, a Fast Fourier Transform (FFT) may be performed on the signal related to the operating state of the motor to obtain a magnitude spectrum corresponding to the signal related to the operating state of the motor.

And then, normalizing the amplitude spectrum corresponding to the signal related to the running state of the motor to obtain a normalized amplitude spectrum corresponding to the signal related to the running state of the motor. In one approach, each amplitude value in the amplitude spectrum corresponding to the signal related to the operating state of the motor may be divided by the amplitude value corresponding to the zero frequency to obtain a normalized amplitude spectrum corresponding to the signal related to the operating state of the motor. The amplitude value corresponding to the zero frequency may be referred to as a dc component of the amplitude spectrum, that is, the normalization method in this step is to remove other components by using the dc component in the amplitude spectrum.

a₂And acquiring intensity information and/or distribution information of the signal according to the normalized amplitude spectrum corresponding to the signal related to the running state of the motor.

The following describes the acquisition of the intensity information and/or distribution information of the signal from the normalized amplitude spectrum, respectively.

First, a method of acquiring intensity information of the signal from the normalized amplitude spectrum will be described.

Specifically, obtaining the intensity information of the signal according to the normalized magnitude spectrum corresponding to the signal includes: and acquiring the intensity information according to the normalized magnitude spectrum corresponding to the signal and M preset thresholds, wherein the intensity information comprises M intensity values, and M is an integer greater than or equal to 1.

Wherein, according to the normalized amplitude spectrum corresponding to the signal and M preset thresholds, the intensity information is obtained, which includes: and for any one first preset threshold in the M preset thresholds, obtaining the sum of the difference values of each amplitude value in the normalized amplitude spectrum and the first preset threshold, wherein the sum of the difference values of each amplitude value in the normalized amplitude spectrum and the first preset threshold is the intensity value corresponding to the first preset threshold in the intensity information. It is understood that the number of intensity values included in the intensity information may be determined according to the number of preset thresholds.

Optionally, each preset threshold value in the M preset threshold values can be any value from 0 to 1.

Exemplarily, M — 3, where the intensity information includes 3 intensity values; further, 3 preset thresholds are preset to be 0, 0.1, 0.2. Adding the amplitude values of which the amplitude values are larger than 0 in the normalized amplitude spectrum to obtain an intensity value E corresponding to a preset threshold value 0 in the intensity information₁₁Adding the difference value of 0.1 to each amplitude value in the normalized amplitude spectrum to obtain an intensity value E corresponding to a preset threshold value of 0.1 in the intensity information₁₂Adding the difference value of 0.2 to each amplitude value in the normalized amplitude spectrum to obtain an intensity value E corresponding to a preset threshold value of 0.2 in the intensity information₁₃。E₁₁、E₁₂And E₁₃For 3 intensity values in the intensity information obtained from the normalized magnitude spectrum, i.e., E₁₁、E₁₂And E₁₃The intensity information described above is composed.

Next, the distribution information of the signal obtained from the normalized amplitude spectrum corresponding to the signal related to the operating state of the motor will be described.

Specifically, acquiring distribution information of a signal related to the operating state of the motor according to a normalized amplitude spectrum corresponding to the signal, including:

b1, obtaining a distribution signal corresponding to the signal according to the normalized amplitude spectrum corresponding to the signal.

Specifically, obtaining a distribution signal corresponding to the signal according to the normalized amplitude spectrum corresponding to the signal includes:

in one mode, the normalized magnitude spectrum is subjected to an inverse cosine transform to obtain a distribution signal corresponding to the signal. Other kinds of transformations (such as inverse fourier transformation, etc.) may be performed on the normalized magnitude spectrum to obtain a distribution signal corresponding to the signal, which is not limited in this embodiment. The profile signal can be a cepstrum signal corresponding to the signal relating to the operating state of the electric machine. The distribution signal corresponding to the signal related to the motor running state can represent the composition of the signal related to the motor running state, and represents the frequency distribution condition of the signal related to the motor running state.

In another mode, to reduce the complexity of the calculation, obtaining a distribution signal corresponding to the signal according to the normalized amplitude spectrum corresponding to the signal includes:

b11, down-sampling the normalized amplitude spectrum to obtain a signal after down-sampling the normalized amplitude spectrum.

Triangular window downsampling can be carried out on the normalized amplitude spectrum to obtain a signal obtained after the normalized amplitude spectrum is downsampled. The triangular window down-sampling can be triangular window uniform down-sampling. The triangular window downsampling can refer to the schematic diagram of the triangular window downsampling in fig. 4.

In a specific embodiment, the down-sampled signal of the normalized magnitude spectrum can be obtained by the following formula:

win(i)＝|D-|i|| (2)

wherein G (j) is a signal obtained by adding the triangular window downsampling to the normalized amplitude spectrum, floor (×) is an operation of rounding, R is a motor rotation speed, fs is a sampling frequency of the signal (i.e., the sampling frequency of the signal obtained in the step S201 and in the motor running state), N is a length of a first sub-signal for obtaining the first normalized amplitude spectrum, G (×) is a first normalized amplitude spectrum, and win (i) is a triangular window function; j is the abscissa of the signal after the triangular window downsampling of the normalized amplitude spectrum, wherein the abscissa can be the number of sampling points or the frequency, and is not limited herein;

it is understood that, the normalized amplitude may also be down-sampled by adding other kinds of windows, so as to obtain a signal obtained by down-sampling the normalized amplitude spectrum, which is not limited in this embodiment.

b12, obtaining a distribution signal corresponding to the signal related to the running state of the motor according to the signal obtained by down-sampling the normalized amplitude spectrum.

Specifically, the signal obtained by down-sampling the normalized magnitude spectrum may be subjected to inverse cosine transform to obtain the distribution signal. The distribution signal may also be obtained by performing other kinds of transforms (such as inverse fourier transform, etc.) on the signal obtained by down-sampling the normalized magnitude spectrum, which is not limited in this embodiment.

Specifically, the signal obtained by down-sampling the normalized amplitude spectrum is subjected to inverse cosine transform, and the distribution signal obtained can be realized by the following formula:

wherein, C_kFor the distribution signal, k is the abscissa of the distribution signal, which may be the reciprocal frequency.

b2, determining the first K distribution values in the distribution signal as the distribution information of the signal related to the running state of the motor.

For example, if the expression of the distribution signal is shown in equation (5), K is 1, …, and K is sequentially substituted into equation (5), and the first K distribution values of the distribution signal can be obtained: c₁,…,C_k,…,C_KThen C is₁,…,C_k,…,C_KThe distribution information of the distribution signal is composed.

And step S203, acquiring the running state of the motor according to the intensity information and/or the distribution information of the signal.

Specifically, in one embodiment: acquiring the running state of the motor corresponding to the energy information and/or the distribution information according to the intensity information and/or the distribution information of the signal, wherein the running state comprises the following steps:

and acquiring the running state of the motor corresponding to the intensity information and/or the distribution information by adopting a machine learning algorithm according to the intensity information and/or the distribution information of the signal and a machine learning model. The machine learning model is obtained by adopting the machine learning algorithm and training based on a plurality of training samples and labels of the training samples, the training samples comprise strength information and/or distribution information of signals related to the running state of the first motor, and the labels of the training samples are used for indicating the running state of the first motor.

Specifically, the intensity information and/or the distribution information obtained in the step are used as input of a machine learning model, and a target label is output after calculation by adopting a machine learning algorithm, wherein the target label is used for indicating the running state of the motor.

It is understood that when the operating state of the motor corresponding to the intensity information is acquired using a machine learning algorithm based on the intensity information of the signal and a machine learning model, the training sample includes the intensity information of the signal related to the operating state of the first motor. When the running state of the motor corresponding to the distribution information is obtained by adopting a machine learning algorithm according to the distribution information of the signal and a machine learning model, the training sample comprises the distribution information of the signal related to the running state of the first motor. When the operating state of the motor corresponding to the distribution information and the intensity information is acquired by a machine learning algorithm according to the distribution information, the intensity information and a machine learning model of the signal, the training sample includes the intensity information and the distribution information of the signal related to the operating state of the first motor.

The method adopts the machine learning method to obtain the running state of the motor, and the accuracy rate of the obtained running state of the motor is higher.

In another embodiment: according to the intensity information and/or the distribution information of the signal, the operation state of the motor corresponding to the intensity information and/or the distribution information is acquired, and the following three conditions exist:

and I, acquiring the running state of the motor corresponding to the intensity information according to the intensity information of the signal.

Specifically, acquiring the operating state of the motor corresponding to the strength information according to the strength information of the signal includes: and acquiring the running state of the motor corresponding to the intensity information according to the intensity information of the signal and a preset corresponding relation, wherein the preset corresponding relation comprises various preset intensity information and the running state corresponding to each preset intensity information. The method specifically comprises the following steps: determining target preset intensity information corresponding to the intensity information; and determining the running state corresponding to the target preset intensity information in the preset corresponding relation as the running state of the motor.

Exemplarily, if the intensity information includes a first intensity value corresponding to a zero value, a second intensity value corresponding to a second preset threshold and a third intensity value corresponding to the first preset threshold, where the first preset threshold is smaller than the second preset threshold, the respective corresponding operating states of the 5 kinds of preset intensity information and the 5 kinds of preset intensity information included in the preset correspondence relationship are as follows:

(1) first preset intensity information: the first intensity value is smaller than a first preset intensity value; the running state corresponding to the first preset intensity information is abnormal starting of the motor.

Specifically, the first preset intensity value may be any value between 0.3 and 0.7, such as 0.5.

Since the first intensity value is an intensity value corresponding to a zero value, according to the method for obtaining the intensity value in step S202, the first intensity value is a total intensity value of the signal related to the operation state of the motor, and the first intensity value may indicate the total intensity value of the signal related to the operation state of the motor, therefore, when the first intensity value is smaller than the first preset intensity value, the total intensity value of the signal related to the operation state of the motor may be considered to be smaller, and thus, the corresponding operation state may be a start abnormality of the motor.

(2) Second preset intensity information: the first intensity value is greater than or equal to a first preset intensity value and less than or equal to a second preset intensity value, and the second intensity value is greater than a third preset intensity value; the operation state corresponding to the second preset intensity information is that the risk of abnormal operation exists in the first time period.

Specifically, the second preset intensity value may be any value from 2.5 to 3.5, such as 3. The third predetermined intensity value may be any value from 0.02 to 0.07, such as 0.05.

Since the second intensity value is an intensity value corresponding to the second preset threshold, and the second preset threshold is greater than the first preset threshold, it can be known from the method for obtaining the intensity value in step S202 that the second intensity value may indicate the total intensity of the signal segment with relatively high intensity in the signal related to the operation state of the motor. Therefore, when the first intensity value is greater than or equal to the first preset intensity value and less than or equal to the second preset intensity value, the total intensity of the signal related to the operation state of the motor can be considered to be moderate, the second intensity value is greater than the third preset intensity value, the total intensity of the signal segment with relatively greater intensity in the signal related to the operation state of the motor can be considered to be greater, and the intensity of certain frequency positions in the signal related to the operation state of the motor is relatively greater, so that the corresponding operation state at this time can be a risk of operation abnormality in the first time period.

(3) Third preset intensity information: the first intensity value is greater than or equal to a first preset intensity value and less than or equal to a second preset intensity value, the second intensity value is less than or equal to a third preset intensity value, and the difference between the third intensity value and the second intensity value is less than or equal to a fourth preset intensity value; and the running state corresponding to the third preset intensity information is that the motor runs normally.

Specifically, the fourth preset intensity value may be any value from 0.3 to 0.7, such as 0.5.

Since the third strength value is the strength value corresponding to the first preset threshold, and the second preset threshold is greater than the first preset threshold, according to the method for obtaining strength values in step S202, the third strength value can indicate the total strength of the signal segment with relatively moderate strength of the signal related to the operation state of the motor, therefore, when the first strength value is greater than or equal to the first preset strength value and less than or equal to the second preset strength value, the total strength of the signal related to the operation state of the motor can be considered moderate, the second strength value is less than or equal to the third preset strength value, the total strength of the signal segment with relatively high strength in the signal related to the operation state of the motor can be considered small, that is, the strength of the signal segment with relatively moderate strength in the signal related to the operation state of the motor is relatively large, and the difference between the third strength value and the second strength value is less than the fourth preset strength value, which indicates that the total strength of the signal segment with relatively moderate strength in the signal related to the operation state of the motor is also small, that is, the intensity of the signal at the position where no or few frequencies exist in the signal related to the operation state of the motor is relatively moderate, so that the corresponding operation state may be that the motor operates normally.

(4) Fourth preset intensity information: the first intensity value is greater than or equal to a first preset intensity value and less than or equal to a second preset intensity value, the second intensity value is less than or equal to a third preset intensity value, and the difference between the third intensity value and the second intensity value is greater than or equal to a fourth preset intensity value; the running state corresponding to the fourth preset intensity information is that the risk of running abnormity exists in the second time length.

Specifically, when the first intensity value is greater than or equal to the first preset intensity value and less than or equal to the second preset intensity value, the overall intensity of the signal relating to the operating state of the machine can be considered moderate, the second intensity value being less than or equal to a third preset intensity value, the total intensity of the signal segments of the signal having a relatively large intensity among the signals related to the operating state of the motor can be considered to be small, that is, the intensity of the signal at the position where there is no or few frequencies in the signal related to the operation state of the motor is relatively large, and the difference between the third intensity value and the second intensity value is larger than the fourth preset intensity value, it indicates that the total intensity of the signal segment with relatively moderate intensity in the signal related to the operation state of the motor is large, i.e. the intensity of more frequency locations in the signal relating to the operating state of the electric machine is relatively moderate, the corresponding operating state may then be a risk of an operational anomaly during the second period of time. The second time length is longer than the first time length, namely the intensity of certain frequency positions in the signals related to the running state of the motor is relatively larger, and the intensity of more frequency positions in the signals related to the running state of the motor is relatively moderate, so that the motor is more prone to abnormity.

(5) Fifth preset intensity information: if the first intensity value is larger than the second preset intensity value. The operating state corresponding to the fourth preset intensity information is that the noise of the motor is too large.

Specifically, when the first intensity value is greater than the second preset intensity value, the total intensity of the signals related to the operation state of the motor may be considered to be greater, and thus, the corresponding operation state may be that the noise of the motor is too large at this time.

Under this example: according to the intensity information of the signal, the running state of the motor corresponding to the intensity information is obtained according to a preset corresponding relation, the preset corresponding relation comprises multiple preset intensity information and the running state corresponding to each preset intensity information, and the preset corresponding relation comprises the following steps:

and determining which kind of preset intensity information in the (1) to (5) corresponds to the intensity information according to the first intensity value, the second intensity value and the third intensity value included in the intensity information of the signal, and if the preset intensity information corresponds to the first kind of preset intensity information, determining that the running state of the motor is abnormal starting of the motor corresponding to the first kind of preset intensity information.

II, acquiring the running state of the motor corresponding to the strength information according to the distribution information of the signal, wherein the running state comprises the following steps: and acquiring the running state of the motor corresponding to the distribution information according to the distribution information of the signal and a preset corresponding relation, wherein the preset corresponding relation comprises various preset distribution information and the running state corresponding to each preset distribution information. The method specifically comprises the following steps: determining target preset distribution information corresponding to the distribution information; and determining the running state corresponding to the target preset distribution information in the preset corresponding relation as the running state of the motor.

III, acquiring the running state of the motor corresponding to the distribution information and the intensity information according to the distribution information and the intensity information of the signal, wherein the running state comprises the following steps: and acquiring the running state of the motor corresponding to the distribution information and the intensity information according to the distribution information and the intensity information of the signal and a preset corresponding relation, wherein the preset corresponding relation comprises a plurality of preset characteristic information and the running state corresponding to each preset characteristic information. The preset characteristic information is a plurality of combinations of preset intensity information and preset distribution information. The method specifically comprises the following steps: determining target preset characteristic information corresponding to the distribution information and the strength information; and determining the running state corresponding to the target preset characteristic information in the preset corresponding relation as the running state of the motor.

The implementation mode for acquiring the running state of the motor does not need to train a machine learning model and perform a complex machine learning algorithm, has low requirement on hardware and has higher efficiency of acquiring the running state of the motor compared with the previous mode.

In the embodiment, the running state of the motor is obtained by obtaining the intensity information and/or the distribution information of the signal related to the running state of the motor, the running state of the motor is judged without hearing by human ears, and the running state of the motor can be objectively reflected by the intensity information and/or the distribution information of the signal related to the running state of the motor, so that the efficiency and the accuracy of obtaining the running state of the motor by the method are high.

Another specific implementation of the embodiment shown in fig. 1 is explained below when the characteristic information of the signal relating to the operating state of the electric machine comprises intensity information and/or profile information. Fig. 5 is a flowchart three of a method for acquiring an operating state of a motor according to the embodiment of the present application. Referring to fig. 5, the method of the present embodiment includes:

step S301, acquiring a signal related to the operating state of the motor.

Specifically, the specific implementation of this step is referred to step S101 in the embodiment shown in fig. 1, and is not described here again.

And S302, extracting N sections of sub-signals in the signals related to the running state of the motor, wherein N is an integer greater than or equal to 1.

Specifically, in one mode, in order to obtain more accurate intensity information and/or distribution information of the signal, N may be an integer greater than or equal to 2.

The sub-signal in this embodiment is a segment of the sub-signal with a length smaller than that of the signal, and the length of each segment of the sub-signal is the same. Alternatively, the number of sampling points of each segment of the sub-signal may be 20000.

Illustratively, if the signal is the signal in fig. 2, the N segments of sub-signals are N segments of sub-signals of the signal in fig. 2. Fig. 6 is a schematic diagram of N segments of sub-signals of the signals in fig. 2. Referring to fig. 6, the N-segment sub-signals include: a-b, c-d. The signals between a-b are a segment of the sub-signals of the signals in fig. 2, and the signals between c-d are a segment of the sub-signals of the signals in fig. 2.

And step S303, acquiring the intensity information and/or the distribution information of the signal related to the running state of the motor according to the N sections of sub-signals.

Specifically, acquiring the strength information and/or distribution information of the signal related to the operation state of the motor according to the N segments of sub-signals includes:

and c1, acquiring N normalized amplitude spectrums corresponding to the N sections of sub signals, wherein the N sections of sub signals correspond to the N normalized amplitude spectrums one to one. The N normalized amplitude spectra are the normalized amplitude spectra corresponding to the signal.

Specifically, for any section of first sub-signals in the N sections of sub-signals, obtaining a first normalized magnitude spectrum corresponding to the first sub-signals includes:

c11, acquiring a first amplitude spectrum corresponding to the first sub-signal.

Specifically, Fast Fourier Transform (FFT) may be performed on the first sub-signal to obtain a first amplitude spectrum corresponding to the first sub-signal.

And c12, normalizing the first amplitude spectrum to obtain a first normalized amplitude spectrum.

Specifically, each amplitude value in the first amplitude spectrum may be divided by an amplitude value corresponding to the zero frequency to obtain a first normalized amplitude spectrum. The amplitude value corresponding to the zero frequency may be referred to as a dc component of the first amplitude spectrum, that is, the normalization method in this step is to remove other components by using the dc component in the first amplitude spectrum.

And c2, acquiring the intensity information and/or distribution information of the signal related to the running state of the motor according to the N normalized amplitude spectrums.

The following describes the acquisition of the intensity information and the distribution information of the signal related to the operating state of the motor based on the N normalized amplitude spectra, respectively.

First, a method of acquiring intensity information of a signal related to an operation state of a motor from N normalized amplitude spectra will be described.

Specifically, acquiring intensity information of a signal related to the operating state of the motor according to the N normalized amplitude spectra includes: and acquiring N groups of intensity values according to the N normalized magnitude spectrums, wherein the N normalized magnitude spectrums correspond to the N groups of intensity values one to one. Further, each set of intensity values may include M intensity component values, M being an integer greater than or equal to 1. That is, a set of intensity values can be obtained from each normalized magnitude spectrum, each set of intensity values comprising M intensity component values.

The obtained N sets of intensity values are intensity information of the signal related to the operating state of the motor. The method for obtaining the N sets of intensity values is explained below. Specifically, for any first normalized magnitude spectrum in the N normalized magnitude spectra, according to the first normalized magnitude spectrum, obtaining a first set of intensity values includes: and for any one first preset threshold value in the M preset threshold values, acquiring the sum of difference values of each amplitude value in the first normalized amplitude spectrum and the first preset threshold value, wherein the sum of difference values of each amplitude value in the first normalized amplitude spectrum and the first preset threshold value is the intensity component value corresponding to the first preset threshold value in the first group of intensity information. It is understood that the number of intensity component values in the set of intensity values may be determined according to the number of preset thresholds.

Wherein, each preset threshold value can be any value of 0-1.

Exemplarily, M-3, when the first set of intensity values comprises 3 strong onesA component value; further, 3 preset thresholds are preset to be 0, 0.1, 0.2. Adding the amplitude values with the intensity value larger than 0 in the first normalized amplitude spectrum to obtain an intensity component value E corresponding to a preset threshold value 0 in the first group of intensity values₁₁Adding the sum of the difference values of 0.1 and each amplitude value in the first normalized amplitude spectrum to obtain an intensity component value E corresponding to a preset threshold value of 0.1 in the first group of intensity values₁₂Adding the difference value of 0.2 to each amplitude value in the first normalized amplitude spectrum to obtain an intensity component value E corresponding to a preset threshold value of 0.2 in the first group of intensity values₁₃。E₁₁、E₁₂And E₁₃Is 3 intensity component values of a first set of intensity values obtained from a first normalized magnitude spectrum, i.e., E₁₁、E₁₂And E₁₃The first set of intensity values described above is composed.

Next, a method of acquiring distribution information of signals related to the operating state of the motor from the N normalized amplitude spectra will be described.

Specifically, acquiring distribution information of signals related to the operating state of the motor according to the N normalized amplitude spectra includes:

d₁and acquiring N distribution signals corresponding to signals related to the running state of the motor according to the N normalized amplitude spectrums, wherein the N normalized amplitudes correspond to the N distribution signals one to one.

In one mode, for any one first normalized amplitude spectrum of the N normalized amplitude spectra, the first normalized amplitude spectrum is subjected to inverse cosine transform to obtain a first distribution signal. Other kinds of transforms (such as inverse fourier transform) may be performed on the first normalized amplitude to obtain the first distribution signal, which is not limited in this embodiment.

In another mode, to reduce the complexity of the calculation, for any one first normalized magnitude spectrum of the N normalized magnitude spectra, acquiring a first distribution signal according to the first normalized magnitude spectrum includes:

d₁₁and performing down-sampling on the first normalized amplitude spectrum to obtain a signal obtained after the down-sampling of the first normalized amplitude spectrum.

The down-sampling of the first normalized amplitude spectrum to obtain a signal after down-sampling of the first normalized amplitude spectrum includes: and performing triangular window downsampling on the first normalized amplitude spectrum to obtain a signal obtained after downsampling the first normalized amplitude spectrum. The triangular window down-sampling can be triangular window uniform down-sampling.

It is understood that, the first normalized amplitude may also be subjected to down-sampling with other kinds of windows, so as to obtain a signal obtained by down-sampling the first normalized amplitude spectrum, which is not limited in this embodiment.

d₁₂And obtaining a first distribution signal according to the signal obtained after the first normalized amplitude spectrum is subjected to down-sampling.

Specifically, the signal after the down-sampling of the first normalized magnitude spectrum may be subjected to inverse cosine transform to obtain a first distribution signal. Other kinds of transforms (such as inverse fourier transform) may be performed on the first normalized amplitude to obtain the first distribution signal, which is not limited in this embodiment.

d₂Acquiring N groups of distribution values according to the N distribution signals, wherein each group of distribution values comprises K distribution component values, and the N distribution signals correspond to the N groups of distribution values one to one; k is an integer greater than or equal to 1, optionally, K ═ 5.

Specifically, according to each distribution signal, a set of distribution values can be obtained, each set of distribution values including K distribution component values. The N groups of distribution values are distribution information of signals related to the running state of the motor.

The following describes a method for acquiring distribution information: for any first distribution signal of the N distribution signals, obtaining a first set of distribution values according to the first distribution signal, including: the first K distribution values in the first distribution signal are determined as a first set of distribution values.

And step S304, acquiring the running state of the motor according to the intensity information and/or the distribution information of the signal.

Specifically, in one embodiment: acquiring the running state of the motor corresponding to the intensity information and/or the distribution information according to the intensity information and/or the distribution information of the signal, wherein the running state comprises the following steps:

and acquiring the running state of the motor corresponding to the N groups of intensity values and/or N groups of distribution values by adopting a machine learning algorithm according to the N groups of intensity values and/or N groups of distribution values of the signal and a machine learning model. The machine learning model is obtained by adopting the machine learning algorithm and training based on a plurality of training samples and labels of the training samples, the training samples comprise N groups of intensity values and N groups of distribution values of signals related to the running state of the first motor, and the labels of the training samples are used for indicating the running state of the first motor.

Specifically, the N sets of intensity values and N sets of distribution values obtained in the step are used as input of a machine learning model, and a target label is output after calculation by a machine learning algorithm, wherein the target label is used for indicating the running state of the motor.

It will be appreciated that when a machine learning algorithm is used to obtain the operating state of the motor corresponding to the intensity information based on the N sets of intensity values of the signal and the machine learning model, the training sample includes N sets of intensity values of the signal that are related to the operating state of the first motor. When the running state of the motor corresponding to the N groups of distribution values is obtained by adopting a machine learning algorithm according to the N groups of distribution values of the signal and a machine learning model, the training sample comprises the N groups of distribution values of the signal related to the running state of the first motor. When the operating state of the motor corresponding to the N sets of intensity values and the N sets of distribution values is obtained by a machine learning algorithm according to the N sets of intensity values and the N sets of distribution values of the signal and a machine learning model, the training sample includes the N sets of intensity values and the N sets of distribution values of the signal related to the operating state of the first motor.

Specifically, acquiring the operating state of the motor corresponding to the strength information according to the strength information of the signal includes: and acquiring the running state of the motor corresponding to the N groups of intensity values according to the N groups of intensity values of the signal and a preset corresponding relation, wherein the preset corresponding relation comprises a plurality of preset intensity information and the running state corresponding to each preset intensity information. The method specifically comprises the following steps: determining target preset intensity information corresponding to the N groups of intensity values; and determining the running state corresponding to the target preset intensity information in the preset corresponding relation as the running state of the motor.

Illustratively, if each of the N sets of intensity values includes an intensity component value corresponding to a zero value, an intensity component value corresponding to a second predetermined threshold and an intensity component value corresponding to a first predetermined threshold, the first predetermined threshold is less than the second predetermined threshold. The preset correspondence is the same as in the corresponding example in the previous embodiment.

And determining which preset intensity information in the (1) to (5) corresponds to the N groups of intensity values according to the N groups of intensity values included in the intensity information of the signal, and if the preset intensity information corresponds to the first type of preset intensity information, determining that the running state of the motor is abnormal starting of the motor corresponding to the first type of preset intensity information.

Specifically, since each of the N sets of intensity values includes the intensity component value corresponding to the zero value, the intensity component value corresponding to the second preset threshold and the intensity component value corresponding to the first preset threshold, there are N intensity component values corresponding to the zero value, N intensity component values corresponding to the second preset threshold, and N intensity component values corresponding to the first preset threshold in total.

Therefore, according to the N sets of strength values included in the strength information of the signal, an average value of N strength component values corresponding to a zero value may be obtained to obtain a first strength value, an average value of N strength component values corresponding to a second preset threshold value may be obtained to obtain a second strength value, and an average value of N strength component values corresponding to the first preset threshold value may be obtained to obtain a third strength value. Next, which of the preset intensity information (1) to (5) above corresponds to the N sets of intensity values is determined based on the first intensity value, the second intensity value, and the third intensity value.

In addition, in other embodiments, according to other suitable algorithms, for example, a median value or a mean square error, the median value or the mean square error of the N intensity component values corresponding to the zero value may be obtained to obtain a first intensity value, the median value or the mean square error of the N intensity component values corresponding to the second preset threshold value may be obtained to obtain a second intensity value, and the median value or the mean square error of the N intensity component values corresponding to the first preset threshold value may be obtained to obtain a third intensity value.

II, acquiring the running state of the motor corresponding to the strength information according to the distribution information of the signal, wherein the running state comprises the following steps: and acquiring the running states of the motors corresponding to the N groups of distribution values according to the N groups of distribution values of the signals and a preset corresponding relation, wherein the preset corresponding relation comprises a plurality of preset distribution information and the running states corresponding to each preset distribution information. The method specifically comprises the following steps: determining target preset distribution information corresponding to the N groups of distribution values; and determining the running state corresponding to the target preset distribution information in the preset corresponding relation as the running state of the motor.

III, acquiring the running state of the motor corresponding to the distribution information and the intensity information according to the distribution information and the intensity information of the signal, wherein the running state comprises the following steps: and acquiring the running states of the motor corresponding to the N groups of intensity values and the N groups of distribution values according to the N groups of intensity values and the N groups of distribution values of the signal and a preset corresponding relationship, wherein the preset corresponding relationship comprises a plurality of preset characteristic information and the running states corresponding to each preset characteristic information. The preset characteristic information is a plurality of combinations of preset intensity information and preset distribution information. The method specifically comprises the following steps: determining target preset information corresponding to the N groups of intensity values and the N groups of distribution values; and determining the running state corresponding to the target preset information in the preset corresponding relation as the running state of the motor.

Further, to enhance the accuracy of the acquired operation state of the motor, the "acquiring a signal related to the operation state of the motor" in the above embodiment includes: a plurality of signals related to the operating state of the motor are acquired within a preset time period. The aforementioned embodiment, wherein the acquiring the operating state of the motor according to the characteristic information of the signal related to the operating state of the motor according to the characteristic information includes: for one first signal in a plurality of signals related to the running state of the motor, acquiring characteristic information of the first signal; and acquiring the running state of the motor according to the characteristic information corresponding to the signals related to the running state of the motor.

Specifically, the plurality of signals related to the operation state of the motor may be the same kind of signals or different kinds of signals.

For each acquired signal related to the motor running state, acquiring feature information of the signal by using the method of the embodiment shown in fig. 3 or fig. 5, acquiring the running states of the motors according to the feature information, namely acquiring the running states of the motors within a preset time, and if the number of the target running states in the acquired running states of the motors is greater than a preset value, determining that the running state of the motors is the target running state; this can enhance the robustness of the above-described operation state acquisition method. It is understood that the preset time period may be set to any value between 0.5 hours and 1 day, or may also be set to 3 to 5 days, or even longer, in other embodiments, there may be a plurality of signals partially overlapping with each other related to the operation state of the motor, and the preset time period may be set according to actual needs, and is not limited herein.

Illustratively, 10 signals relating to the operating state of the motor are acquired within a preset time period, with a preset value of 5. The method of the embodiment shown in fig. 3 or fig. 5 is adopted to acquire the motor running state 10 times according to 10 signals related to the motor running state, and 10 motor running states are obtained. And if 6 of the 10 motor running states are too high in motor noise, determining that the motor running state is too high in motor noise.

The method for acquiring the motor operating state provided by the embodiment of the present application is described above with reference to fig. 1 to 6, and a device for acquiring the motor operating state is described below with reference to a specific embodiment.

Fig. 7 is a first schematic structural diagram of an apparatus for acquiring an operating state of a motor according to an embodiment of the present application; referring to fig. 7, the device 600 for acquiring the motor operating state of the present embodiment includes: a memory 61, a processor 62 and a communication bus 63 through which the memory 61 and the processor 62 are connected;

a memory 61 for storing a computer program;

a processor 62 for invoking the computer program to perform the following operations:

acquiring a signal related to the running state of the motor;

Where the processor 62 may be a CPU, the processor 62 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or any conventional processor or the like.

The device for acquiring the running state of the motor in this embodiment may be used to implement the technical solutions in the above embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.

Fig. 8 is a schematic structural diagram ii of an apparatus for acquiring an operating state of a motor according to an embodiment of the present application; referring to fig. 8, the device 600 for acquiring the motor operating state according to the present embodiment further includes, on the basis of the device shown in fig. 7: a signal collector 64 and a motor 65 connected with the processor through the communication bus 63;

the signal collector 64 is configured to collect a signal related to an operation state of the motor 65;

the processor 62 is specifically configured to perform the following operations when acquiring the signal related to the operating state of the motor:

signals relating to the operating state of the motor 65 are acquired from the signal collector 64.

Wherein the signal collector 64 may comprise at least one of: microphone, accelerometer, vibration sensor, piezoelectric crystal, barometer, ampere meter, inertial measurement unit.

Optionally, the processor 62 is further configured to, when acquiring the characteristic information of the signal, perform the following operations:

the signal is pre-processed.

Optionally, the preprocessing includes performing normalization processing on the signal to obtain a normalized signal.

Optionally, the characteristic information includes strength information and/or distribution information of the signal, and the processor 62 is specifically configured to, when acquiring the characteristic information of the signal and acquiring the operating state of the motor according to the characteristic information, perform the following operations:

acquiring intensity information and/or distribution information of the signal;

and acquiring the running state of the motor according to the intensity information and/or the distribution information of the signals.

Optionally, when the processor 62 acquires the strength information and/or the distribution information of the signal, it is specifically configured to perform the following operations:

acquiring a normalized amplitude spectrum corresponding to the signal;

and acquiring the intensity information and/or distribution information of the signal according to the normalized amplitude spectrum corresponding to the signal.

Optionally, when obtaining the normalized magnitude spectrum corresponding to the signal, the processor 62 is specifically configured to perform the following operations:

acquiring a magnitude spectrum corresponding to the signal;

and dividing each amplitude value in the amplitude spectrum by the amplitude value corresponding to the zero frequency to obtain the normalized amplitude spectrum.

Optionally, when the processor 62 acquires the intensity information of the signal according to the normalized magnitude spectrum corresponding to the signal, it is specifically configured to perform the following operations:

and acquiring the intensity information according to the normalized amplitude spectrum corresponding to the signal and M preset thresholds, wherein the intensity information comprises M intensity values, and M is an integer greater than or equal to 1.

Optionally, when the processor 62 acquires the intensity information according to the normalized amplitude spectrum corresponding to the signal and M preset thresholds, it is specifically configured to perform the following operations:

and for any one first preset threshold in the M preset thresholds, obtaining the sum of the difference values of each amplitude value in the normalized amplitude spectrum and the first preset threshold, wherein the sum of the difference values of each amplitude value and the first preset threshold is the intensity value corresponding to the first preset threshold in the intensity information.

Optionally, the preset threshold is any value from 0 to 1.

Optionally, when the processor 62 acquires the distribution information of the signal according to the normalized magnitude spectrum corresponding to the signal, it is specifically configured to perform the following operations:

obtaining a distribution signal corresponding to the signal according to the normalized amplitude spectrum corresponding to the signal;

and determining the first K distribution values in the distribution signal as the distribution information of the signal, wherein K is an integer greater than or equal to 1.

Optionally, when obtaining the distribution signal corresponding to the signal according to the normalized amplitude spectrum corresponding to the signal, the processor 62 is specifically configured to perform the following operations:

down-sampling the normalized amplitude spectrum to obtain a signal after down-sampling the normalized amplitude spectrum;

and obtaining a distribution signal corresponding to the signal according to the signal obtained after the normalized amplitude spectrum is subjected to down-sampling.

Optionally, when obtaining the distribution signal corresponding to the signal according to the signal obtained by down-sampling the normalized amplitude spectrum, the processor 62 is specifically configured to perform the following operations:

and performing inverse cosine transform on the signal subjected to the down-sampling of the normalized amplitude spectrum to obtain a distribution signal corresponding to the signal.

Optionally, when the processor 62 down-samples the normalized amplitude spectrum to obtain a signal obtained by down-sampling the normalized amplitude spectrum, it is specifically configured to perform the following operations:

and performing triangular window downsampling on the normalized amplitude spectrum to obtain a signal obtained after downsampling the normalized amplitude spectrum.

Optionally, the triangular window down-sampling is triangular window uniform down-sampling.

Optionally, the motor includes at least one of the operating states, the characteristic information of the signal is acquired, and the processor 62 is specifically configured to perform the following operations when acquiring the operating state of the motor according to the characteristic information:

and acquiring characteristic information of the signal, and acquiring the running state of the motor corresponding to the characteristic information according to a preset corresponding relation according to the characteristic information, wherein the preset corresponding relation is the running state comprising a plurality of preset characteristic information and each preset characteristic information.

Optionally, when the processor 62 obtains the running state of the motor corresponding to the feature information according to the feature information and a preset corresponding relationship, the processor is specifically configured to perform the following operations:

determining target preset feature information corresponding to the feature information, wherein the target preset feature information is feature information in the preset feature information;

and determining the running state corresponding to the target preset information in the preset corresponding relation as the running state of the motor.

Optionally, the at least one operating condition is at least one of:

the motor is abnormally started, the motor runs abnormally after a first time, the motor runs normally, the motor runs abnormally after a second time, and the noise in the running process of the motor is overlarge;

wherein the first duration is less than the second duration.

Optionally, when the operating state of the motor corresponding to the characteristic information is obtained according to the characteristic information, the processor 62 is specifically configured to perform the following operations:

and acquiring the running state of the motor corresponding to the characteristic information by adopting a machine learning algorithm according to the characteristic information and a machine learning model.

Optionally, the machine learning algorithm is a neural network algorithm, and the machine learning model is a neural network model.

Optionally, the signal related to the operating state of the electric machine is one or more of:

the noise signal of the motor, the current signal of the motor and the signal obtained by measuring by an inertia measuring unit arranged on the outer wall of the motor.

Optionally, the noise signal of the motor is collected by a microphone, an accelerometer, a vibration sensor, a piezoelectric crystal and/or a barometer.

Optionally, the processor 62 is specifically configured to, when acquiring the signal related to the operating state of the motor, perform the following operations:

acquiring a plurality of signals related to the running state of the motor within a preset time length;

when the processor 62 acquires the characteristic information of the signal and acquires the operating state of the motor according to the characteristic information, the following operations are specifically performed:

for a first signal in the plurality of signals, acquiring characteristic information of the first signal;

and acquiring the running state of the motor according to the characteristic information corresponding to the signals. The device for acquiring the running state of the motor in this embodiment may be used to implement the technical solutions in the above embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.

Embodiments of the present application also provide a computer-readable storage medium, which includes a program or instructions, and when the program or instructions are run on a computer, the method described in the above method embodiments is executed.

An embodiment of the present application further provides an electronic device, which includes a motor and the obtaining device for obtaining the operating state of the motor as described above. The device for acquiring the running state of the motor in this embodiment may be used to implement the technical solutions in the above embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.

In one embodiment, the electronic device may be any electronic device requiring motor driving, such as a radar, an unmanned aerial vehicle, an electric fan system, and the like, wherein the radar may be a mechanical scanning lidar, and the unmanned aerial vehicle may be an unmanned aerial vehicle, an unmanned ship, and the like, which are not limited herein.

Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.

Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims

A method for acquiring the running state of a motor is characterized by comprising the following steps:

acquiring a signal related to the running state of the motor;

and acquiring the characteristic information of the signal, and acquiring the running state of the motor according to the characteristic information.
The method of claim 1, wherein obtaining the characteristic information of the signal further comprises:

the signal is pre-processed.
The method of claim 2, wherein the pre-processing comprises normalizing the signal to obtain a normalized signal.
The method according to claim 1, wherein the characteristic information includes intensity information and/or distribution information of the signal, and the acquiring the characteristic information of the signal, and the acquiring the operating state of the motor according to the characteristic information includes:

acquiring intensity information and/or distribution information of the signal;

and acquiring the running state of the motor according to the intensity information and/or the distribution information of the signals.
The method of claim 4, wherein obtaining the strength information and/or distribution information of the signal comprises:

acquiring a normalized amplitude spectrum corresponding to the signal;

and acquiring the intensity information and/or distribution information of the signal according to the normalized amplitude spectrum corresponding to the signal.
The method of claim 5, wherein obtaining a normalized magnitude spectrum corresponding to the signal comprises:

acquiring a magnitude spectrum corresponding to the signal;

and dividing each amplitude value in the amplitude spectrum by the amplitude value corresponding to the zero frequency to obtain the normalized amplitude spectrum.
The method according to claim 5, wherein the obtaining the intensity information of the signal according to the normalized amplitude spectrum corresponding to the signal comprises:

and acquiring the intensity information according to the normalized magnitude spectrum corresponding to the signal and M preset thresholds, wherein the intensity information comprises M intensity values, and M is an integer greater than or equal to 1.
The method according to claim 7, wherein the obtaining the intensity information according to the normalized amplitude spectrum corresponding to the signal and M preset thresholds comprises:

and for any one first preset threshold in the M preset thresholds, obtaining the sum of the difference values of each amplitude value in the normalized amplitude spectrum and the first preset threshold, wherein the sum of the difference values of each amplitude value and the first preset threshold is the intensity value corresponding to the first preset threshold in the intensity information.
The method according to claim 8, wherein the preset threshold value is any value from 0 to 1.
The method according to claim 5, wherein the obtaining distribution information of the signal according to the normalized magnitude spectrum corresponding to the signal comprises:

obtaining a distribution signal corresponding to the signal according to the normalized amplitude spectrum corresponding to the signal;

and determining the first K distribution values in the distribution signal as the distribution information of the signal, wherein K is an integer greater than or equal to 1.
The method according to claim 10, wherein obtaining the distribution signal corresponding to the signal according to the normalized magnitude spectrum corresponding to the signal comprises:

down-sampling the normalized amplitude spectrum to obtain a signal after down-sampling the normalized amplitude spectrum;

and obtaining a distribution signal corresponding to the signal according to the signal obtained after the normalized amplitude spectrum is subjected to down-sampling.
The method according to claim 11, wherein obtaining a distribution signal corresponding to the signal from the signal obtained by down-sampling the normalized magnitude spectrum comprises:

and performing inverse cosine transform on the signal subjected to the down-sampling of the normalized amplitude spectrum to obtain a distribution signal corresponding to the signal.
The method of claim 11, wherein the down-sampling the normalized magnitude spectrum to obtain a signal down-sampled from the normalized magnitude spectrum comprises:

and performing triangular window downsampling on the normalized amplitude spectrum to obtain a signal obtained after downsampling the normalized amplitude spectrum.
The method of claim 13, wherein the triangular window downsampling is triangular window uniform downsampling.
The method of claim 1, wherein the obtaining characteristic information of the signal and obtaining the operating state of the motor according to the characteristic information comprises:

extracting N segments of subsignals of the signal; wherein N is an integer greater than or equal to 1;

and acquiring the characteristic information of the signal according to the N sections of sub-signals, and acquiring the running state of the motor according to the characteristic information.
The method of claim 1, wherein the motor includes at least one of the operating states, and wherein obtaining the characterization information of the signal and obtaining the operating state of the motor based on the characterization information comprises:

and acquiring characteristic information of the signal, and acquiring the running state of the motor corresponding to the characteristic information according to a preset corresponding relation according to the characteristic information, wherein the preset corresponding relation is the running state comprising a plurality of preset characteristic information and each preset characteristic information.
The method according to claim 16, wherein acquiring the operating state of the motor corresponding to the characteristic information according to a preset corresponding relationship based on the characteristic information comprises:

determining target preset feature information corresponding to the feature information, wherein the target preset feature information is feature information in the preset feature information;

and determining the running state corresponding to the target characteristic preset information in the preset corresponding relation as the running state of the motor.
The method of claim 16, wherein the at least one of the operating conditions is at least one of:

the motor is abnormally started, the motor runs abnormally after a first time, the motor runs normally, the motor runs abnormally after a second time, and the noise in the running process of the motor is overlarge;

wherein the first duration is less than the second duration.
The method according to claim 1, wherein the acquiring the operating state of the motor corresponding to the characteristic information according to the characteristic information includes:

and acquiring the running state of the motor corresponding to the characteristic information by adopting a machine learning algorithm according to the characteristic information and a machine learning model.
The method of claim 19, wherein the machine learning algorithm is a neural network algorithm and the machine learning model is a neural network model.
A method according to any of claims 1 to 20, wherein the signal relating to the operating state of the electrical machine is one or more of:

the noise signal of the motor, the current signal of the motor and the signal obtained by measuring by an inertia measuring unit arranged on the outer wall of the motor.
The method of claim 21, wherein the noise signal of the motor is collected by a microphone, an accelerometer, a vibration sensor, a piezoelectric crystal, and/or a barometer.
The method of claim 21, wherein obtaining signals related to an operating condition of the electric machine comprises:

acquiring a plurality of signals related to the running state of the motor within a preset time length;

the acquiring the characteristic information of the signal and acquiring the running state of the motor according to the characteristic information comprises the following steps:

for one first signal in the plurality of signals related to the running state of the motor, acquiring characteristic information of the first signal;

and acquiring the running state of the motor according to the characteristic information corresponding to the signals related to the running state of the motor.
An apparatus for acquiring an operation state of a motor, comprising: a memory, a processor, and a communication bus through which the memory and the processor are connected;

a memory for storing a computer program;

a processor for invoking the computer program to perform the following operations:

acquiring a signal related to the running state of the motor;

and acquiring the characteristic information of the signal, and acquiring the running state of the motor according to the characteristic information.
The apparatus of claim 24, further comprising a signal collector and a motor connected to the processor via the communication bus

The signal collector is used for collecting signals related to the running state of the motor;

the processor is specifically configured to perform the following operations when acquiring the signal related to the operating state of the motor:

and acquiring a signal related to the running state of the motor from the signal collector.
The apparatus of claim 24, wherein the processor, when obtaining the characteristic information of the signal, is further configured to:

the signal is pre-processed.
The apparatus of claim 26, wherein the pre-processing comprises normalizing the signal to obtain a normalized signal.
The apparatus according to claim 24, wherein the characteristic information includes strength information and/or distribution information of the signal, and the processor is specifically configured to, when acquiring the characteristic information of the signal and acquiring the operating state of the motor according to the characteristic information, perform the following operations:

acquiring intensity information and/or distribution information of the signal;

and acquiring the running state of the motor according to the intensity information and/or the distribution information of the signals.
The apparatus according to claim 28, wherein the processor is configured to, when acquiring the strength information and/or the distribution information of the signal, perform the following operation:

acquiring a normalized amplitude spectrum corresponding to the signal;

and acquiring the intensity information and/or distribution information of the signal according to the normalized amplitude spectrum corresponding to the signal.
The apparatus according to claim 29, wherein the processor, when obtaining the normalized magnitude spectrum corresponding to the signal, is specifically configured to:

acquiring a magnitude spectrum corresponding to the signal;

and dividing each amplitude value in the amplitude spectrum by the amplitude value corresponding to the zero frequency to obtain the normalized amplitude spectrum.
The apparatus according to claim 29, wherein the processor is specifically configured to perform the following operations when obtaining the intensity information of the signal according to the normalized magnitude spectrum corresponding to the signal:

and acquiring the intensity information according to the normalized magnitude spectrum corresponding to the signal and M preset thresholds, wherein the intensity information comprises M intensity values, and M is an integer greater than or equal to 1.
The apparatus according to claim 31, wherein the processor is specifically configured to perform the following operations when obtaining the intensity information according to the normalized amplitude spectrum corresponding to the signal and M preset thresholds:

and for any one first preset threshold in the M preset thresholds, obtaining the sum of the difference values of each amplitude value in the normalized amplitude spectrum and the first preset threshold, wherein the sum of the difference values of each amplitude value and the first preset threshold is the intensity value corresponding to the first preset threshold in the intensity information.
The device of claim 32, wherein the preset threshold is any value from 0 to 1.
The apparatus according to claim 29, wherein the processor, when acquiring the distribution information of the signal according to the normalized magnitude spectrum corresponding to the signal, is specifically configured to:

obtaining a distribution signal corresponding to the signal according to the normalized amplitude spectrum corresponding to the signal;

and determining the first K distribution values in the distribution signal as the distribution information of the signal, wherein K is an integer greater than or equal to 1.
The apparatus according to claim 34, wherein the processor is specifically configured to perform the following operations when obtaining the distribution signal corresponding to the signal according to the normalized amplitude spectrum corresponding to the signal:

down-sampling the normalized amplitude spectrum to obtain a signal after down-sampling the normalized amplitude spectrum;

and obtaining a distribution signal corresponding to the signal according to the signal obtained after the normalized amplitude spectrum is subjected to down-sampling.
The apparatus according to claim 35, wherein the processor is specifically configured to perform the following operations when obtaining the distribution signal corresponding to the signal from the signal obtained by down-sampling the normalized amplitude spectrum:

and performing inverse cosine transform on the signal subjected to the down-sampling of the normalized amplitude spectrum to obtain a distribution signal corresponding to the signal.
The apparatus as claimed in claim 35, wherein the processor is configured to perform the following operations when down-sampling the normalized magnitude spectrum to obtain a down-sampled signal of the normalized magnitude spectrum:

and performing triangular window downsampling on the normalized amplitude spectrum to obtain a signal obtained after downsampling the normalized amplitude spectrum.
The apparatus of claim 39, wherein said triangular window down-sampling is triangular window uniform down-sampling.
The apparatus of claim 24, wherein the motor comprises at least one of the operating states, wherein the processor is configured to obtain the characteristic information of the signal, and wherein the processor is specifically configured to, when obtaining the operating state of the motor according to the characteristic information, perform the following operations:

and acquiring characteristic information of the signal, and acquiring the running state of the motor corresponding to the characteristic information according to a preset corresponding relation according to the characteristic information, wherein the preset corresponding relation is the running state comprising a plurality of preset characteristic information and each preset characteristic information.
The apparatus as claimed in claim 39, wherein the processor is specifically configured to perform the following operations when obtaining the operating state of the motor corresponding to the characteristic information according to the preset corresponding relationship based on the characteristic information:

determining target preset feature information corresponding to the feature information, wherein the target preset feature information is feature information in the preset feature information;

and determining the running state corresponding to the target preset information in the preset corresponding relation as the running state of the motor.
The apparatus of claim 39, wherein the at least one of the operating conditions is at least one of:

the motor is abnormally started, the motor runs abnormally after a first time, the motor runs normally, the motor runs abnormally after a second time, and the noise in the running process of the motor is overlarge;

wherein the first duration is less than the second duration.
The apparatus according to claim 25, wherein the processor, when obtaining the operating state of the motor corresponding to the characteristic information according to the characteristic information, is specifically configured to:

and acquiring the running state of the motor corresponding to the characteristic information by adopting a machine learning algorithm according to the characteristic information and a machine learning model.
The apparatus of claim 42, wherein the machine learning algorithm is a neural network algorithm and the machine learning model is a neural network model.
An apparatus according to any one of claims 24 to 43 wherein the signal relating to the operating condition of the motor is one or more of:

the noise signal of the motor, the current signal of the motor and the signal obtained by measuring by an inertia measuring unit arranged on the outer wall of the motor.
The apparatus of claim 44, wherein the noise signal of the motor is collected by a microphone, an accelerometer, a vibration sensor, a piezoelectric crystal, and/or a barometer.
The apparatus of claim 44, wherein the processor, when obtaining the signal related to the operating state of the motor, is configured to perform operations comprising:

acquiring a plurality of signals related to the running state of the motor within a preset time length;

the processor is specifically configured to, when acquiring the characteristic information of the signal and acquiring the operating state of the motor according to the characteristic information, perform the following operations:

for a first signal in the plurality of signals, acquiring characteristic information of the first signal;

and acquiring the running state of the motor according to the characteristic information corresponding to the signals.
A computer readable storage medium comprising a program or instructions for performing the method of any of claims 1 to 23 when the program or instructions are run on a computer.
An electronic device comprising a motor and the device for acquiring the operation state of the motor according to any one of claims 24 to 46, wherein the device is used for acquiring the operation state of the motor.
The electronic device of claim 48, wherein the electronic device is a radar or a drone.