Driving motor state monitoring method and device, electronic equipment and storage medium

Abstract

The invention provides a driving motor state monitoring method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining motor monitoring data of a driving motor, inputting the motor monitoring data into a digital twin model of the driving motor, and obtaining an actual observation state parameter, the digital twin model being used for representing a motor characteristic relation of the simulation driving motor; parameter estimation is conducted on the actual observation state parameters and the operation control data through particle filtering, estimated state parameters are obtained, the estimated state parameters comprise at least one parameter estimated value, the at least one parameter estimated value is compared with a corresponding preset parameter threshold value, and the state of the driving motor is obtained. The parameter estimation value is used for representing an estimation value of inherent monitoring characteristics of the driving motor; interference of noise on motor state monitoring is reduced through the digital twin model and the particle filter, the accuracy, the real-time performance and the monitoring efficiency of nonlinear state monitoring are improved, and therefore the risk of safety accidents of vehicles is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of motor monitoring, and in particular to a method, device, electronic device and storage medium for monitoring the state of a drive motor. Background Art

[0002] At present, with the development and popularization of new energy vehicles, electric vehicles have become the mainstream direction of future automobile development. However, the failure rate of the drive motor system of electric vehicles is relatively high. How to effectively monitor and diagnose the status of the motor system has become an important research topic. Traditional fault detection methods mainly rely on manual experience, which is difficult to adapt to complex working conditions and changing environments. Moreover, most of them can only diagnose faults when they occur, which has a delay. In recent years, digital twin technology has been widely used in vehicle system modeling and state estimation, and has achieved certain results. Digital twin is to simulate the mechanism and appearance of the physical entity of the research object through digital simulation means, so that the state of the research object that is difficult to observe during operation can be presented intuitively, so as to better analyze the research object and formulate appropriate operation and maintenance strategies.

[0003] At present, due to the influence of factors such as nonlinearity and noise interference in drive motor status monitoring, it is not possible to achieve real-time and accurate monitoring of the drive motor status through digital twin technology. Summary of the invention

[0004] The present application provides a drive motor state monitoring method, device, electronic device and storage medium to solve the above-mentioned technical problem that the drive motor state cannot be accurately monitored in real time.

[0005] In one embodiment of the present application, the present application provides a method for monitoring the state of a drive motor, including: obtaining motor monitoring data of the drive motor, the motor monitoring data including operation control data, sensory acquisition data and motor inherent data; inputting the motor monitoring data into a digital twin model of the drive motor to obtain actual observed state parameters, the digital twin model being used to characterize and simulate the motor characteristic relationship of the drive motor; performing parameter estimation on the actual observed state parameters and the operation control data through particle filtering to obtain estimated state parameters, the estimated state parameters including at least one parameter estimation value; comparing the at least one parameter estimation value with a corresponding preset parameter threshold to obtain the state of the drive motor, the parameter estimation value being used to characterize the estimated value of the inherent monitoring characteristic of the drive motor.

[0006] In one embodiment of the present application, the at least one parameter estimation value is compared with the corresponding preset parameter threshold value to obtain the drive motor state, including: if all parameter estimation values ​​meet the range of the preset parameter threshold value, the drive motor state is determined to be a normal motor to obtain new motor monitoring data to continue the drive motor state monitoring; if there is at least one parameter estimation value that does not meet the range of the preset parameter threshold value, the drive motor state is determined to be an abnormal motor to generate an abnormal prompt information.

[0007] In one embodiment of the present application, the motor monitoring data is input into the digital twin model of the drive motor to obtain actual observed state parameters, including: if the motor characteristic relationship is a torque characteristic relationship, the first monitoring data is input into the torque twin model to obtain the value of the rotor flux; if the motor characteristic relationship is a speed characteristic relationship, the second monitoring data is input into the speed twin model to obtain the value of the friction coefficient; if the motor characteristic relationship is a quadrature-axis characteristic relationship and a direct-axis characteristic relationship, the third monitoring data and the value of the rotor flux are input into the electrical twin model to obtain electrical characteristic values, and the electrical characteristic values ​​include the value of the direct-axis component of inductance, the value of the quadrature-axis component of inductance and the value of the stator resistance; wherein the digital twin model includes the torque twin model, the speed twin model and the electrical twin model, the actual observed state parameters include the value of the rotor flux, the value of the friction coefficient and at least one of the electrical characteristic values, and the motor monitoring data includes the first monitoring data, the second monitoring data and the third monitoring data.

[0008] In one embodiment of the present application, the method for determining the digital twin model includes: if the motor characteristic relationship is a torque characteristic relationship, the torque twin model is determined according to the number of permanent magnet pole pairs, the stator quadrature-axis current, the rotor flux and the motor torque; if the motor characteristic relationship is a speed characteristic relationship, the speed twin model is determined according to the angular acceleration, the moment of inertia, the motor torque, the external load torque, the friction coefficient and the motor speed; if the motor characteristic relationship is a direct-axis characteristic relationship, the speed twin model is determined according to the stator resistance, the stator direct-axis current, the inductance direct-axis component, the electrical angular velocity, the inductance quadrature-axis component, the stator ... The direct-axis twin model is determined by the direct-axis current and the stator direct-axis voltage; if the motor characteristic relationship is a quadrature-axis characteristic relationship, the quadrature-axis twin model is determined according to the stator resistance, the stator quadrature-axis current, the inductance quadrature-axis component, the electrical angular velocity, the inductance direct-axis component, the stator direct-axis current, the rotor flux and the stator quadrature-axis voltage; wherein the digital twin model includes the torque twin model, the speed twin model, the direct-axis twin model and the quadrature-axis twin model, the inductance direct-axis component and the inductance quadrature-axis component are equal, and the electrical twin model includes the direct-axis twin model and the quadrature-axis twin model.

[0009] In one embodiment of the present application, the actual observed state parameters and the operation control data are estimated by particle filtering to obtain estimated state parameters, including: obtaining multiple previous moment state parameters and multiple previous moment state weights corresponding to the actual observed state parameters; performing state transfer on each of the previous moment state parameters according to a preset state transfer relationship, a preset process noise relationship and the operation control data to obtain multiple current moment state parameters; performing state observation on each of the current moment state parameters according to a preset observation relationship and a preset measurement noise relationship to obtain multiple expected observed state parameters; updating the previous moment state weights corresponding to each of the current moment state parameters based on the actual observed state parameters and each of the expected observed state parameters to obtain multiple current moment state weights; and performing weighted summation of each of the current moment state weights and each of the current moment state parameters to obtain an estimated state parameter.

[0010] In one embodiment of the present application, a weighted sum is performed on each current moment state weight and each current moment state parameter to obtain an estimated state parameter, including: normalizing each current moment state weight to obtain a plurality of normalized state weights; resampling each current moment state parameter based on each normalized state weight to obtain a plurality of sampled state weights and a plurality of sampled state parameters; and weighted summing each sampled state parameter according to each sampled state weight to obtain an estimated state parameter.

[0011] In one embodiment of the present application, the actual observed state parameters and the operation control data are estimated by particle filtering, and before the estimated state parameters are obtained, the method also includes: acquiring historical monitoring data of the drive motor; correcting the transfer parameters of the initial state transfer relationship according to the historical monitoring data to obtain a preset state transfer relationship; correcting the observation parameters of the initial observation relationship according to the historical monitoring data to obtain a preset observation relationship; wherein the initial state transfer relationship is used to characterize the influence of different historical control data on the temporal evolution of at least one inherent monitoring feature, and the initial observation relationship is used to map the current state parameters to the observation space.

[0012] In one embodiment of the present application, the present application provides a drive motor state monitoring device, including: a data acquisition module, used to acquire motor monitoring data of the drive motor, the motor monitoring data including operation control data, sensory acquisition data and motor inherent data; a model calculation module, used to input the motor monitoring data into the digital twin model of the drive motor to obtain actual observed state parameters, and the digital twin model is used to characterize and simulate the motor characteristic relationship of the drive motor; a particle estimation module, used to perform parameter estimation on the actual observed state parameters and the operation control data through particle filtering to obtain estimated state parameters, and the estimated state parameters include at least one parameter estimation value; a state determination module, used to compare the at least one parameter estimation value with the corresponding preset parameter threshold to obtain the drive motor state, and the parameter estimation value is used to characterize the estimated value of the inherent monitoring characteristic of the drive motor.

[0013] In one embodiment of the present application, the present application provides an electronic device, which includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device implements the drive motor state monitoring method as described in any of the above embodiments.

[0014] In one embodiment of the present application, the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor of a computer, the computer executes the drive motor state monitoring method described in any one of the above embodiments.

[0015] Beneficial effects of the embodiments of the present application: The present application provides a drive motor state monitoring method, device, electronic device and storage medium. The embodiments of the present application simulate the characteristics of the drive motor through a digital twin model to obtain real-time actual observed state parameters, and perform particle filtering through the actual observed state parameters and operation control data to obtain estimated state parameters, so as to monitor the motor state by estimating the state parameters, which can reduce the interference of noise on motor state monitoring, improve the accuracy, real-time and monitoring efficiency of nonlinear state monitoring, and thus reduce the risk of vehicle safety accidents.

[0016] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0018] Figure 1 A schematic diagram showing an exemplary system architecture to which the technical solution of the embodiments of the present application can be applied;

[0019] Figure 2 A schematic diagram of a process of a drive motor state monitoring method according to an embodiment of the present application is shown;

[0020] Figure 3 A schematic structural diagram of a three-phase permanent magnet synchronous motor according to an embodiment of the present application is shown;

[0021] Figure 4 A schematic diagram of a digital twin model according to an embodiment of the present application is shown;

[0022] Figure 5 A block diagram of a drive motor state monitoring device according to an embodiment of the present application is shown;

[0023] Figure 6 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0024] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0025] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0026] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0027] See also Figure 1 , Figure 1 A schematic diagram of an exemplary system architecture to which the technical solution of the embodiment of the present application can be applied is shown. Figure 1 As shown, the system architecture may include a computer device 101 and a sensor 102. The computer device 101 may be at least one of a microcomputer, an embedded computer, a neural network computer, etc., and the number and type of sensors are multiple. The sensor 102 is used to transmit the sensed motor monitoring data to the computer device 101 to monitor the motor status.

[0028] Exemplarily, the computer device 101 obtains motor monitoring data of the drive motor, the motor monitoring data including operation control data, sensory acquisition data and motor inherent data; the motor monitoring data is input into the digital twin model of the drive motor to obtain actual observed state parameters, and the digital twin model is used to characterize the motor characteristic relationship of the simulated drive motor; parameter estimation is performed on the actual observed state parameters and the operation control data through particle filtering to obtain estimated state parameters, and the estimated state parameters include at least one parameter estimation value; at least one parameter estimation value is compared with a corresponding preset parameter threshold to obtain the drive motor state, and the parameter estimation value is used to characterize the estimated value of the inherent monitoring characteristics of the drive motor.

[0029] In related technologies, due to the influence of factors such as nonlinearity and noise interference in drive motor status monitoring, it is impossible to achieve real-time and accurate monitoring of the drive motor status through digital twin technology.

[0030] In order to solve the above technical problems, the present application provides a drive motor state monitoring method, device, electronic device and storage medium. The implementation details of the technical solution of the embodiment of the present application are elaborated in detail below.

[0031] See also Figure 2 , Figure 2 FIG. 2 shows a flow chart of a method for monitoring the state of a drive motor according to an embodiment of the present application. Figure 2 As shown, in an exemplary embodiment, the driving motor state monitoring method includes at least steps S210 to S240, which are described in detail as follows:

[0032] Step S210, obtaining motor monitoring data of the drive motor.

[0033] Among them, motor monitoring data includes operation control data, perception collection data and motor inherent data.

[0034] In one embodiment of the present application, the drive motor includes a three-phase permanent magnet synchronous motor.

[0035] In one embodiment of the present application, the operation control data is used to characterize the data for controlling the operation of the drive motor, such as the motor speed and the motor torque. The sensing acquisition data is used to characterize the data collected by various sensors, such as the three-phase current, the three-phase voltage and the motor rotor position. The motor inherent data is used to characterize the data of the drive motor that does not change with the working conditions, such as the number of permanent magnet pole pairs and the fixed moment of inertia.

[0036] In one embodiment of the present application, the drive motor may also be equipped with an adjustable moment of inertia.

[0037] Step S220: input the motor monitoring data into the digital twin model of the drive motor to obtain actual observed state parameters.

[0038] Among them, the digital twin model is used to characterize the motor characteristic relationship of the simulated drive motor.

[0039] In one embodiment of the present application, the method for determining the digital twin model includes: if the motor characteristic relationship is a torque characteristic relationship, the torque twin model is determined according to the number of permanent magnet pole pairs, the stator quadrature axis current, the rotor flux and the motor torque; if the motor characteristic relationship is a speed characteristic relationship, the speed twin model is determined according to the angular acceleration, the moment of inertia, the motor torque, the external load torque, the friction coefficient and the motor speed; if the motor characteristic relationship is a direct axis characteristic relationship, the speed twin model is determined according to the stator resistance, the stator direct axis current, the inductance direct axis component, the electrical angular velocity, the inductance quadrature axis current ... The direct-axis twin model is determined according to the stator quadrature-axis component, the stator quadrature-axis current and the stator direct-axis voltage; if the motor characteristic relationship is a quadrature-axis characteristic relationship, the quadrature-axis twin model is determined according to the stator resistance, the stator quadrature-axis current, the inductance quadrature-axis component, the electrical angular velocity, the inductance direct-axis component, the stator direct-axis current, the rotor flux and the stator quadrature-axis voltage; among them, the digital twin model includes a torque twin model, a speed twin model, a direct-axis twin model and a quadrature-axis twin model, the inductance direct-axis component and the inductance quadrature-axis component are equal, and the electrical twin model includes a direct-axis twin model and a quadrature-axis twin model.

[0040] In one embodiment of the present application, the digital twin model includes a twin physical model and a twin data model of the drive motor.

[0041] In one embodiment of the present application, a twin physical model is established according to the structure of the vehicle drive motor, and the twin physical model includes a speed twin model and a torque twin model. The twin physical model of the drive motor can be constructed through the simulink simulation module of Matlab.

[0042] In one embodiment of the present application, a twin data model is constructed according to the electrical parameters of the drive motor, such as a direct-axis twin model and a cross-axis twin model, that is, an electrical twin model.

[0043] In one embodiment of the present application, see Figure 3 , Figure 3 FIG. 1 shows a schematic diagram of the structure of a three-phase permanent magnet synchronous motor according to an embodiment of the present application. Figure 3 As shown, Ru, Rv, and Rw represent the resistance in the three-phase winding of the motor, Lu, Lv, and Lw represent the self-inductance coefficient in the three-phase winding of the motor, Uu, Uv, and Uw represent the voltage in the three-phase winding of the motor, iu, iv, and iw represent the stator current in the three-phase winding of the motor, q is the quadrature axis, and d is the direct axis, thereby establishing a twin physical model.

[0044] In one embodiment of the present application, the torque twin model is shown as follows:

[0045]

[0046] Among them, T r is the motor torque, P n is the number of permanent magnet pole pairs, i q is the stator quadrature axis current, is the rotor flux.

[0047] In one embodiment of the present application, in a permanent magnet synchronous motor, the rotor flux is used to characterize the magnetic flux generated by the permanent magnet.

[0048] In one embodiment of the present application, the speed twin model is shown as follows:

[0049]

[0050] in, is the angular acceleration, J is the moment of inertia, T r is the motor torque, T load is the external load torque, μ CoF is the friction coefficient, n r is the motor speed.

[0051] In one embodiment of the present application, see Figure 4 , Figure 4 FIG. 1 shows a schematic diagram of a digital twin model according to an embodiment of the present application. Figure 4As shown, the motor speed and motor torque are external inputs, which can be calculated through the three-phase current, three-phase voltage, and motor rotor position collected by the rotary transformer; iα, iβ are current values ​​obtained by Clarke transformation of the three-phase current of the drive motor, so as to convert the three-phase coordinate system corresponding to the ABC coordinate system into the two-phase stationary coordinate system corresponding to the α-β coordinate system; id, iq are current values ​​obtained by Park transformation of the drive motor, so as to convert the two-phase stationary coordinate system corresponding to the α-β coordinate system into the two-phase rotating coordinate system corresponding to the dq coordinate system; n r Represents the motor speed, T r represents the motor torque; the θ collected by the resolver is the angular position of the rotor relative to the stator; the motor speed is controlled by proportional-integral (PI) to output the quadrature-axis control current i qr , based on i qr The stator quadrature-axis current is subjected to quadrature-axis PI current control to obtain the stator quadrature-axis voltage, and the stator direct-axis voltage is subjected to direct-axis PI current control based on the initial direct-axis control current with a current value of 0 and the stator direct-axis current to obtain the stator direct-axis voltage; the data after Park inverse transformation of the stator direct-axis voltage and the stator direct-axis voltage are respectively input into space vector pulse width modulation (SVPWM) to control the rotor rotation of the drive motor through SVPWM and a three-phase inverter.

[0052] In one embodiment of the present application, the direct axis twin model is shown as follows:

[0053]

[0054] Among them, u d is the stator direct axis voltage, R is the stator resistance, i d is the stator direct axis current, L d is the direct axis component of inductance, ω e is the electrical angular velocity, L q is the quadrature axis component of inductance, i q is the stator quadrature axis current.

[0055] In one embodiment of the present application, the cross-axis twin model is shown as follows:

[0056]

[0057] Among them, u q is the stator quadrature axis voltage, R is the stator resistance, i q is the stator quadrature axis current, L q is the quadrature axis component of inductance, ω e is the electrical angular velocity, L dis the direct axis component of inductance, i d is the stator direct axis current, is the rotor flux.

[0058] In one embodiment of the present application, the motor monitoring data is input into the digital twin model of the drive motor to obtain the actual observed state parameters, including: if the motor characteristic relationship is a torque characteristic relationship, the first monitoring data is input into the torque twin model to obtain the value of the rotor flux; if the motor characteristic relationship is a speed characteristic relationship, the second monitoring data is input into the speed twin model to obtain the value of the friction coefficient; if the motor characteristic relationship is a quadrature-axis characteristic relationship and a direct-axis characteristic relationship, the third monitoring data and the value of the rotor flux are input into the electrical twin model to obtain the electrical characteristic value, and the electrical characteristic value includes the value of the direct-axis component of the inductance, the value of the quadrature-axis component of the inductance and the value of the stator resistance; wherein the digital twin model includes a torque twin model, a speed twin model and an electrical twin model, the actual observed state parameters include at least one of the value of the rotor flux, the value of the friction coefficient and the electrical characteristic value, and the motor monitoring data includes the first monitoring data, the second monitoring data and the third monitoring data.

[0059] Step S230, performing parameter estimation on the actual observed state parameters and the operation control data through particle filtering to obtain estimated state parameters.

[0060] The estimated state parameter includes at least one parameter estimation value.

[0061] In one embodiment of the present application, parameter estimation is performed on actual observed state parameters and operation control data through particle filtering to obtain estimated state parameters, including: obtaining multiple previous moment state parameters and multiple previous moment state weights corresponding to the actual observed state parameters; performing state transfer on each previous moment state parameter according to a preset state transfer relationship, a preset process noise relationship and the operation control data to obtain multiple current moment state parameters; performing state observation on each current moment state parameter according to a preset observation relationship and a preset measurement noise relationship to obtain multiple expected observed state parameters; updating the previous moment state weight corresponding to each current moment state parameter based on the actual observed state parameters and each expected observed state parameter to obtain multiple current moment state weights; and performing weighted summation of each current moment state weight and each current moment state parameter to obtain an estimated state parameter.

[0062] In one embodiment of the present application, multiple previous moment state parameters and multiple previous moment state weights corresponding to the actual observed state parameters are obtained, including: if the monitoring moment of the actual observed state parameters is the initial moment, then multiple initial state parameters randomly generated based on a preset prior distribution are used as multiple previous moment state parameters, and multiple previous moment state weights are determined according to the number of each initial state parameter; if the monitoring moment of the actual observed state parameters is not the initial moment, then multiple previous moment state parameters and multiple previous moment state weights corresponding to the monitoring moment are obtained.

[0063] In one embodiment of the present application, n1 pairs of initial state parameters x0 are randomly generated based on a preset prior distribution.

[0064] In one embodiment of the present application, the inherent monitoring characteristics include rotor flux linkage Friction coefficient μ CoF , stator resistance R, inductance direct axis component L d and the quadrature axis component of the inductance L q .

[0065] In one embodiment of the present application, particles at different times are used to characterize motor state parameters at different times composed of at least one inherent monitoring feature.

[0066] In one embodiment of the present application, the state parameter at the previous moment is also the particle at the previous moment, the initial state parameter is also the initial particle, and the state parameter at the current moment is also the particle at the current moment.

[0067] In one embodiment of the present application, the actual observed state parameter is used to characterize a model calculated value of at least one inherent monitoring feature in the drive motor.

[0068] In one embodiment of the present application, the weight of the initial state parameter is 1.

[0069] In one embodiment of the present application, the preset prior distribution includes a Gaussian distribution, and the probability density function of the Gaussian distribution is as follows:

[0070]

[0071] Among them, f1(x0) is the probability density of the initial state parameter x0, δ 2 is the variance, and u is the disturbance mean.

[0072] In one embodiment of the present application, a state space model is established, including a state equation and an observation equation.

[0073] In one embodiment of the present application, before the actual observed state parameters and operation control data are estimated by particle filtering and the estimated state parameters are obtained, the method also includes: acquiring historical monitoring data of the drive motor; correcting the transfer parameters of the initial state transfer relationship according to the historical monitoring data to obtain a preset state transfer relationship; correcting the observation parameters of the initial observation relationship according to the historical monitoring data to obtain a preset observation relationship; wherein the initial state transfer relationship is used to characterize the influence of different historical control data on the temporal evolution of the motor state parameters, and the initial observation relationship is used to map the current state parameters to the observation space.

[0074] In one embodiment of the present application, a state space model of the drive motor is established, and the state space model includes a state transition model and a state observation model. The state transition model is used to determine the state parameters at the current moment, and the state observation model is used to determine the expected observed state parameters.

[0075] In one embodiment of the present application, the historical monitoring data includes experimental data of three-phase current, three-phase voltage, and motor rotor position under various operating conditions. Different operating conditions include different temperatures, different motor speeds, different motor loads, and the like.

[0076] In one embodiment of the present application, the determination of multiple current state parameters is as follows:

[0077] X T =f2(X T-1 ,μ T ,w T ) Formula (6)

[0078] Among them, X T is all the current state parameters x at time T T The set of f2 is the preset state transition relationship, X T-1 is the set of state parameters before time T-1, μ T Input the corresponding operation control data for the system at time T, w T is the process noise value at time T.

[0079] In one embodiment of the present application, the determination of multiple expected observation state parameters is as follows:

[0080] Y T =h(X T ,n T ) Formula (7)

[0081] Among them, Y T is all expected observation state parameters y at time T T A collection of h, h is the preset observation relationship, X T For all current state parameters xT The collection of n T is the observation noise value at time T.

[0082] In one embodiment of the present application, the process noise value is determined as follows:

[0083]

[0084] Among them, p(w T ) is the process noise value w at time T T The probability density of , n2 is the dimension of the state parameters at the current moment, and |Q| is the determinant of the covariance matrix Q.

[0085] In one embodiment of the present application, the covariance matrix is ​​determined as follows:

[0086]

[0087] Among them, Q is the covariance matrix, R t is the stator resistance at time t, is the rotor flux at time t.

[0088] In one embodiment of the present application, the current state weight is determined as follows:

[0089]

[0090] in, is the current state weight corresponding to the current state parameter at the i-th time t, is the state weight of the previous moment corresponding to the state parameter of the previous moment at the i-th moment t-1, is the observation likelihood function corresponding to the current state parameter at the i-th time t, n1 is the total number of state parameters at the current time, z t is the actual observed state parameter at time t.

[0091] In one embodiment of the present application, Based on the actual observed state parameter z at time t t and the expected observed state parameter y at time t t get.

[0092] In one embodiment of the present application, a weighted sum is performed on each current moment state weight and each current moment state parameter to obtain an estimated state parameter, including: normalizing each current moment state weight to obtain a plurality of normalized state weights; resampling each current moment state parameter based on each normalized state weight to obtain a plurality of sampled state weights and a plurality of sampled state parameters; and weighted summing each sampled state parameter according to each sampled state weight to obtain an estimated state parameter.

[0093] In one embodiment of the present application, the normalized state weight is determined as follows:

[0094]

[0095] in, is the normalized state weight corresponding to the current state parameter at the i-th time t, is the current state weight corresponding to the current state parameter at the i-th time t, and n1 is the total number of current state parameters.

[0096] In one embodiment of the present application, a resampling threshold is set, and N particles whose initial sampling weight is greater than the resampling threshold are screened out to obtain multiple sampling state parameters. The resampling threshold is determined as follows:

[0097]

[0098] Among them, N th is the resampling threshold, is the normalized state weight corresponding to the current state parameter at the i-th time t, and n1 is the total number of state parameters at the current time.

[0099] In one embodiment of the present application, the sampling state weight corresponding to the sampling state parameter is determined as follows:

[0100]

[0101] in, is the sampling state weight of the sampling state parameter at the i-th time t, and N is the total number of sampling state parameters.

[0102] In one embodiment of the present application, the estimated state parameter is determined as follows:

[0103]

[0104] in, To estimate the state parameters, is the sampling state parameter at the i-th moment t, is the sampling state weight of the sampling state parameter at the i-th time t, and N is the total number of sampling state parameters.

[0105] Step S240: compare at least one parameter estimation value with a corresponding preset parameter threshold to obtain a driving motor state.

[0106] The parameter estimation value is used to characterize the estimation value of the inherent monitoring characteristic of the drive motor.

[0107] In one embodiment of the present application, at least one parameter estimation value is compared with a corresponding preset parameter threshold value to obtain a drive motor state, including: if all parameter estimation values ​​satisfy the range of the preset parameter threshold value, the drive motor state is determined to be a normal motor to obtain new motor monitoring data to continue drive motor state monitoring; if there is at least one parameter estimation value that does not satisfy the range of the preset parameter threshold value, the drive motor state is determined to be an abnormal motor to generate abnormal prompt information.

[0108] In one embodiment of the present application, the abnormal prompt information is used to alarm and remind the driver to take corresponding measures.

[0109] In one embodiment of the present application, the present application updates the parameters of the digital twin model in real time through the three-phase current, three-phase voltage, and rotor position information collected by various sensors of the drive motor, and combines the particle filter algorithm to estimate the parameters, and finally performs real-time state monitoring of the drive motor. Compared with the traditional drive motor state detection method, the drive motor state monitoring based on digital twin and particle filter algorithm can monitor and diagnose in real time when the drive motor is working, can realize digital diagnosis and detection, and improve real-time performance, monitoring efficiency and monitoring accuracy.

[0110] See also Figure 5 , Figure 5 A block diagram of a drive motor state monitoring device according to an embodiment of the present application is shown. The device can be applied to Figure 1 The implementation environment shown in the figure is specifically configured in the computer device 101. The device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applied.

[0111] like Figure 5 As shown, a drive motor state monitoring device 500 according to an embodiment of the present application includes: a data acquisition module 501 , a model calculation module 502 , a particle estimation module 503 and a state determination module 504 .

[0112] The data acquisition module 501 is used to acquire the motor monitoring data of the drive motor, and the motor monitoring data includes operation control data, sensing collection data and motor inherent data;

[0113] A model calculation module 502 is used to input the motor monitoring data into the digital twin model of the drive motor to obtain actual observed state parameters. The digital twin model is used to characterize the motor characteristic relationship of the simulated drive motor;

[0114] A particle estimation module 503 is used to perform parameter estimation on the actual observed state parameters and the operation control data through particle filtering to obtain estimated state parameters, where the estimated state parameters include at least one parameter estimation value;

[0115] The state determination module 504 is used to compare at least one parameter estimation value with a corresponding preset parameter threshold value to obtain the state of the drive motor, wherein the parameter estimation value is used to characterize an estimation value of an inherent monitoring feature of the drive motor.

[0116] It should be noted that the drive motor state monitoring device provided in the above embodiment and the drive motor state monitoring method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment, and will not be repeated here. In practical applications, the drive motor state monitoring device provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0117] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by one or more processors, the electronic device implements the drive motor state monitoring method provided in the above-mentioned embodiments.

[0118] See also Figure 6 , Figure 6 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Figure 6 The computer system 600 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0119] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage part 608 to the random access memory (RAM) 603, such as executing the method in the above embodiment. In the random access memory 603, various programs and data required for system operation are also stored. The central processing unit 601, the read-only memory 602 and the random access memory 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0120] The following components are connected to the input / output interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read therefrom is installed into the storage section 608 as needed.

[0121] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 609, and / or installed from a removable medium 611. When the computer program is executed by a central processing unit (CPU) 601, various functions defined in the system of the present application are executed.

[0122] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0123] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0124] The units involved in the embodiments described in the present application can be implemented by software or by hardware, and the units described can also be set in a processor. Among them, the names of these units do not constitute a limitation on the units themselves under certain circumstances. Therefore, the technical solution according to the implementation mode of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including a number of instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation mode of the present application.

[0125] Another aspect of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes the drive motor state monitoring method provided in each of the above embodiments. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently without being assembled into the electronic device.

[0126] In the above embodiments, unless otherwise specified, describing common objects by using serial numbers such as "first" and "second" only indicates that they refer to different instances of the same object, rather than indicating that the objects being described must adopt a given order, whether in time, space, sorting or any other way.

[0127] The above embodiments are merely illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A method for monitoring the state of a drive motor, characterized in that: The method comprises: Acquire motor monitoring data of the drive motor, wherein the motor monitoring data includes operation control data, sensing collection data and motor inherent data; Inputting the motor monitoring data into the digital twin model of the drive motor to obtain actual observed state parameters, wherein the digital twin model is used to characterize and simulate the motor characteristic relationship of the drive motor; Performing parameter estimation on the actual observed state parameter and the operation control data by particle filtering to obtain an estimated state parameter, wherein the estimated state parameter includes at least one parameter estimation value; The at least one parameter estimation value is compared with a corresponding preset parameter threshold value to obtain a state of the drive motor, wherein the parameter estimation value is used to characterize an estimation value of an inherent monitoring feature of the drive motor.

2. The driving motor state monitoring method according to claim 1, characterized in that: Comparing the at least one parameter estimation value with a corresponding preset parameter threshold to obtain a driving motor state includes: If all parameter estimation values ​​meet the range of preset parameter thresholds, the drive motor state is determined to be normal, so as to obtain new motor monitoring data and continue to monitor the drive motor state; If there is at least one parameter estimation value that does not meet the range of the preset parameter threshold, the driving motor state is determined as a motor abnormality to generate abnormal prompt information.

3. The driving motor state monitoring method according to claim 1, characterized in that: Inputting the motor monitoring data into the digital twin model of the drive motor to obtain actual observed state parameters, including: If the motor characteristic relationship is a torque characteristic relationship, the first monitoring data is input into the torque twin model to obtain the value of the rotor flux; If the motor characteristic relationship is a speed characteristic relationship, the second monitoring data is input into the speed twin model to obtain a value of the friction coefficient; If the motor characteristic relationship is a quadrature-axis characteristic relationship and a direct-axis characteristic relationship, the third monitoring data and the value of the rotor flux are input into the electrical twin model to obtain electrical characteristic values, wherein the electrical characteristic values ​​include the value of the direct-axis component of the inductance, the value of the quadrature-axis component of the inductance, and the value of the stator resistance; Among them, the digital twin model includes the torque twin model, the speed twin model and the electrical twin model, the actual observed state parameters include the value of the rotor flux, the value of the friction coefficient and at least one of the electrical characteristic values, and the motor monitoring data includes the first monitoring data, the second monitoring data and the third monitoring data.

4. The driving motor state monitoring method according to claim 3, characterized in that: The digital twin model is determined by: If the motor characteristic relationship is a torque characteristic relationship, a torque twin model is determined according to the number of permanent magnet pole pairs, the stator quadrature axis current, the rotor flux and the motor torque; If the motor characteristic relationship is a speed characteristic relationship, a speed twin model is determined according to angular acceleration, moment of inertia, motor torque, external load torque, friction coefficient and motor speed; If the motor characteristic relationship is a direct-axis characteristic relationship, a direct-axis twin model is determined according to the stator resistance, the stator direct-axis current, the inductance direct-axis component, the electrical angular velocity, the inductance quadrature-axis component, the stator quadrature-axis current and the stator direct-axis voltage; If the motor characteristic relationship is a quadrature axis characteristic relationship, a quadrature axis twin model is determined according to the stator resistance, the stator quadrature axis current, the quadrature axis component of the inductance, the electrical angular velocity, the direct axis component of the inductance, the stator direct axis current, the rotor flux and the stator quadrature axis voltage; Among them, the digital twin model includes the torque twin model, the speed twin model, the direct-axis twin model and the quadrature-axis twin model, the direct-axis component of inductance and the quadrature-axis component of inductance are equal, and the electrical twin model includes the direct-axis twin model and the quadrature-axis twin model.

5. The driving motor state monitoring method according to any one of claims 1 to 4, characterized in that: Performing parameter estimation on the actual observed state parameters and the operation control data through particle filtering to obtain estimated state parameters includes: Obtaining a plurality of state parameters at a previous moment and a plurality of state weights at a previous moment corresponding to the actually observed state parameters; Performing state transfer on each of the state parameters at the previous moment according to the preset state transfer relationship, the preset process noise relationship and the operation control data to obtain a plurality of current moment state parameters; Performing state observation on each of the current state parameters according to a preset observation relationship and a preset measurement noise relationship to obtain a plurality of expected observation state parameters; Based on the actual observed state parameter and each of the expected observed state parameters, the previous moment state weight corresponding to each of the current moment state parameters is updated to obtain a plurality of current moment state weights; The weighted sum of each current moment state weight and each current moment state parameter is performed to obtain an estimated state parameter.

6. The driving motor state monitoring method according to claim 5, characterized in that: Performing a weighted summation on each current state weight and each current state parameter to obtain an estimated state parameter, including: Normalizing each current state weight to obtain a plurality of normalized state weights; Resample each of the current state parameters based on each of the normalized state weights to obtain a plurality of sampled state weights and a plurality of sampled state parameters; The sampling state parameters are weighted and summed according to the sampling state weights to obtain the estimated state parameter.

7. The driving motor state monitoring method according to claim 5, characterized in that: Before performing parameter estimation on the actual observed state parameter and the operation control data by particle filtering to obtain the estimated state parameter, the method further includes: Acquiring historical monitoring data of the drive motor; Modifying the transfer parameters of the initial state transfer relationship according to the historical monitoring data to obtain a preset state transfer relationship; Correcting the observation parameters of the initial observation relationship according to the historical monitoring data to obtain a preset observation relationship; The initial state transfer relationship is used to characterize the influence of different historical control data on the temporal evolution of at least one inherent monitoring feature, and the initial observation relationship is used to map the current state parameters to the observation space.

8. A drive motor state monitoring device, characterized in that: The device comprises: A data acquisition module, used to acquire motor monitoring data of the drive motor, wherein the motor monitoring data includes operation control data, sensing collection data and motor inherent data; A model calculation module, used for inputting the motor monitoring data into the digital twin model of the drive motor to obtain actual observed state parameters, wherein the digital twin model is used for characterizing and simulating the motor characteristic relationship of the drive motor; A particle estimation module, used for performing parameter estimation on the actual observed state parameter and the operation control data through particle filtering to obtain an estimated state parameter, wherein the estimated state parameter includes at least one parameter estimation value; The state determination module is used to compare the at least one parameter estimation value with the corresponding preset parameter threshold value to obtain the state of the drive motor, wherein the parameter estimation value is used to characterize the estimation value of the inherent monitoring characteristic of the drive motor.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the electronic device to implement the drive motor state monitoring method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is enabled to execute the drive motor state monitoring method according to any one of claims 1 to 7.

Images