Servo integrated machine fault detection method and servo integrated machine thereof

Abstract

The present application relates to servo integrated machine fault diagnosis technical field, especially to a kind of servo integrated machine fault detection method and servo integrated machine thereof, method includes: the coupling dynamics model of servo motor and cavity structure is built;Three-phase stator current signal and three-phase stator voltage signal when servo motor is running are collected, and d, q axis current component i d 、 q It is obtained by Clarke transformation and Park transformation, the electromagnetic torque T e When servo motor is running is calculated by motor electromagnetic equation;The specific frequency when cavity structure vibration is abnormal is obtained by coupling dynamics model, based on specific frequency, three-phase stator current signal, three-phase stator voltage signal and electromagnetic torque T e It is carried out FFT transformation and processing, and the characteristic quantity of different electrical signals under specific frequency is obtained;All characteristic quantities are normalized and diagnosed, and fault recognition is carried out to servo integrated machine, the present application improves detection reliability and detection precision, robustness is high, and it is convenient to implement.

Description

Technical Field

[0001] This invention relates to the field of servo all-in-one machine fault diagnosis technology, and in particular to a servo all-in-one machine fault detection method and the servo all-in-one machine thereof. Background Technology

[0002] With the accelerating pace of automation and intelligentization in global manufacturing, the production process is placing increasingly stringent demands on the performance, efficiency, reliability, and integration of actuators. Against this backdrop, servo motors, as innovative intelligent actuators, are gradually becoming the mainstream choice in the industrial sector due to their highly integrated characteristics, and are progressively replacing the traditional separate "motor + external driver" solution.

[0003] Servo all-in-one machines highly integrate core components such as servo motors, drivers, encoders, and communication and control units into a single unit. This structure significantly simplifies installation and wiring, improves anti-interference capabilities and system compactness, and is widely used, especially in robot joints, CNC machine tools, and high-precision positioning platforms. However, the high power density and enclosed structure of servo all-in-one machines also make them more susceptible to mechanical structural failures such as cavity resonance and structural loosening during long-term operation. If these problems are not detected and diagnosed in a timely manner, they may lead to system performance degradation, decreased positioning accuracy, and even equipment damage or safety accidents.

[0004] Existing fault diagnosis methods for servo integrated machines typically rely on external vibration or acoustic sensors, manual inspection, or simple threshold judgment based on a single electrical quantity. These methods are difficult to implement, have poor reliability, and low detection accuracy in highly integrated, sealed servo integrated machines. Furthermore, the strong coupling of electrical, magnetic, thermal, and mechanical components inside the servo integrated machine results in electrical signals containing both control and switching noise as well as modulation components from structural vibrations. Traditional spectrum analysis methods are easily misled by PWM harmonics, sudden load changes, or speed variations, making it difficult to distinguish between cavity resonance (linear / modal frequency drift) and nonlinear impact faults such as loose bolts. Moreover, they have poor robustness under variable speed and load conditions. Summary of the Invention

[0005] The technical problem to be solved by this invention is to address the existing technical issues of high difficulty in implementing fault detection for servo all-in-one machines, poor reliability, low detection accuracy, and poor robustness.

[0006] Therefore, this invention provides a fault detection method for servo all-in-one machines, which improves detection reliability and accuracy, has high robustness, and is easy to implement.

[0007] A fault detection method for a servo all-in-one machine according to an embodiment of the present invention includes the following steps:

[0008] S1, Construct a coupled dynamic model of the servo motor and the cavity structure;

[0009] S2, Acquires the three-phase stator current signal during servo motor operation. , , and three-phase stator voltage signal , , The d-axis current component i is obtained through Clarke transform and Park transform. d and q-axis current component i q ;

[0010] S3, calculate the electromagnetic torque T of the servo motor during operation using the motor's electromagnetic equations. e ;

[0011] S4, Obtain the specific frequency of abnormal vibration of the cavity structure through a coupled dynamics model. Based on the specific frequency For three-phase stator current signals , , Three-phase stator voltage signal , , and electromagnetic torque T e Perform FFT transformation and processing to obtain a specific frequency. Characteristic quantities of different electrical signals;

[0012] S5 normalizes and diagnoses all feature quantities to identify faults in the servo all-in-one machine.

[0013] The beneficial effect of this invention is that the servo integrated machine fault detection method of this invention, by constructing a coupled dynamic model and analyzing the three-phase stator current signal... , , and three-phase stator voltage signal , , Processing and extracting specific frequencies It can measure the characteristic quantities of different electrical signals without the need for external sensing devices, making it suitable for harsh working conditions such as sealed and explosion-proof environments, thus reducing the difficulty of implementation; in addition, it can measure specific frequencies. This invention fuses and determines the characteristics of different electrical signals, exhibiting strong anti-interference capabilities and environmental adaptability, maintaining accurate detection under varying loads and speeds. Compared to traditional methods, this invention significantly improves real-time performance and implementation costs, effectively avoiding mechanical fatigue or control anomalies caused by cavity structure resonance, reducing maintenance costs, and enhancing the safety and intelligence of the servo integrated machine. It is particularly suitable for online status monitoring and health management of explosion-proof and high-reliability servo systems used in mining.

[0014] According to one embodiment of the present invention, the coupled dynamics model includes:

[0015] The mathematical model of the servo motor in the dq rotating coordinate system is as follows:

[0016] [1]

[0017] in, These are the voltage components along the d-axis and q-axis, respectively. For stator resistance, , These are the stator winding flux linkages for the d-axis and q-axis, respectively. The angular frequency of the stator current rotation;

[0018] The vibration model of the cavity structure is as follows: [2]

[0019] in, For the equivalent mass of the cavity. This is the equivalent displacement in the direction of vibration. For equivalent stiffness, For equivalent damping, This is the torque-structure transmission coefficient;

[0020] The motion equation of the servo motor shaft coupled to the cavity structure via mounting flange, bolts, and housing is as follows:

[0021] [3]

[0022] in, For mechanical inertia, Let t be the mechanical angular velocity and t be the time. For load torque, The coupled disturbance torque generated by the vibration reaction of the cavity structure is calculated using the following formula: ;

[0023] Electromagnetic torque can be expressed as: [4]

[0024] in, This represents the actual motor torque coefficient.

[0025] According to one embodiment of the present invention, the electromagnetic torque T of the servo motor during operation e The calculation formula is:

[0026] [5]

[0027] in, It is a differential operator.

[0028] According to one embodiment of the present invention, based on the specific frequency For three-phase stator current signals , , Three-phase stator voltage signal , , and electromagnetic torque T e Perform FFT transformation and processing to obtain a specific frequency. The characteristic quantities of different electrical signals specifically include:

[0029] Obtain the high-frequency current component in the three-phase stator current : [6]

[0030] in, The amplitude of the sidebands caused by the vibration of the cavity structure. , It is the phase angle of the high-frequency current component;

[0031] Perform an FFT transformation on the three-phase stator current to calculate the energy ratio corresponding to the high-frequency current component. The calculation formula is:

[0032] [7]

[0033] in, This is the sum of the energy of the high-frequency components. It is the sum of all frequency components. The sampling frequency of the servo all-in-one machine. The dividing frequency for the servo all-in-one machine, This refers to the current component at the corresponding frequency.

[0034] Perform an FFT transformation on the three-phase stator voltages to obtain the voltage phase and calculate the phase difference between the voltage and current. and the phase difference with the fundamental frequency of the servo motor Subtraction to obtain phase transition values The calculation formula is:

[0035] [8];

[0036] For the electromagnetic torque T e Perform an FFT transform to obtain a specific frequency. The torque amplitude is used to calculate the equivalent index of the vibration amplitude of the cavity structure according to formula [4]. The calculation formula is:

[0037] [9]

[0038] According to one embodiment of the present invention, step S5 involves fault identification through a set threshold logic and / or through a fault diagnosis model. Fault identification includes:

[0039] If energy ratio When the cavity structure vibrates abnormally at a specific frequency, it increases. When the frequency approaches the structure's natural frequency, the fault type is cavity resonance.

[0040] If the phase abrupt value When the specific frequency changes and the cavity structure vibrates abnormally. If unstable, the fault type is that the cavity structure has become loose;

[0041] If energy ratio and phase change value The equivalent index of the vibration amplitude of the cavity structure appears in all cases. If both increase simultaneously, the fault type is a compound fault.

[0042] According to one embodiment of the present invention, in step S4, adaptive tracking is further performed on a specific frequency when the cavity structure vibrates abnormally, specifically including the following steps:

[0043] Based on the vibration model of the cavity structure, the electromagnetic excitation force is calculated by back-calculating the three-phase stator current fluctuation, and the observation error is obtained. The calculation formula is:

[0044] in, Represents the equivalent displacement in the direction of vibration. The functional relationship with time t, based on Predicted values ​​calculated using recursive least squares or extended Kalman filter algorithms;

[0045] Based on observation error Recursive update parameters The calculation formula is:

[0046]

[0047] in, For cavity equivalent mass The functional relationship with time t, For equivalent stiffness Functional relationship with time t For equivalent damping The functional relationship between time t and K(t) is the gain matrix;

[0048] According to the updated parameters Real-time calculation and updating of specific frequencies when the cavity structure vibrates abnormally. The calculation formula is:

[0049] .

[0050] According to one embodiment of the present invention, the method further includes a self-learning mechanism, specifically comprising:

[0051] When the servo all-in-one machine runs continuously and stably for more than the set period, and the change of the characteristic parameter value is less than 5%, the characteristic range of the stable state is generated according to the characteristic parameter value, and the characteristic range of the stable state is saved as a new threshold template.

[0052] If a slow drift in the value of a characteristic parameter is detected, the specific frequency will be automatically updated when the cavity structure vibrates abnormally.

[0053] According to one embodiment of the present invention, step S2 includes buffering the acquired three-phase stator current signals in a sliding window manner. , , and three-phase stator voltage signal , , and the three-phase stator current signal , , and three-phase stator voltage signal , , Preprocessing is performed.

[0054] A servo all-in-one machine according to an embodiment of the present invention includes:

[0055] Servo all-in-one machine body;

[0056] And a controller electrically connected to the servo all-in-one machine body, the controller being configured to execute the servo all-in-one machine fault detection method as described above.

[0057] According to one embodiment of the present invention, the controller includes a signal acquisition unit, an FPGA unit, and an MCU unit;

[0058] The three-phase stator current signal of the servo motor is synchronously acquired and processed at fixed intervals by the signal acquisition unit. , , and three-phase stator voltage signal , , ;

[0059] The processed three-phase stator current signal is processed by the FPGA unit. , , and three-phase stator voltage signal , , Perform FFT analysis, feature extraction, and adaptive parameter tracking;

[0060] Fault identification and self-learning updates are performed through the MCU unit.

[0061] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0062] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0063] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0064] Figure 1 This is a flowchart of the method according to Embodiment 1 of the present invention.

[0065] Figure 2 This is a schematic diagram of the structure of Embodiment 4 of the present invention.

[0066] Figure 3 This is a schematic diagram of the computer device structure according to Embodiment 5 of the present invention.

[0067] In the diagram: 3. Servo all-in-one machine body; 2. Controller; 21. Signal acquisition unit; 22. FPGA unit; 23. MCU unit; 10. Computer equipment; 1002. Processor; 1004. Memory; 1006. Transmission device. Detailed Implementation

[0068] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0069] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, features defined with "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0070] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0071] Example 1

[0072] This application provides a fault detection method for a servo all-in-one machine, the method including the following steps:

[0073] S1, construct a coupled dynamic model of the servo motor and the cavity structure.

[0074] S2, Acquires the three-phase stator current signal during servo motor operation. , , and three-phase stator voltage signal , , The d-axis current component i is obtained through Clarke transform and Park transform. d and q-axis current component i q .

[0075] S3, calculate the electromagnetic torque T of the servo motor during operation using the motor's electromagnetic equations. e .

[0076] S4, Obtain the specific frequency of abnormal vibration of the cavity structure through a coupled dynamics model. Based on a specific frequency For three-phase stator current signals , , Three-phase stator voltage signal , , and electromagnetic torque T e Perform FFT transformation and processing to obtain a specific frequency. Characteristic quantities of different electrical signals.

[0077] S5 normalizes and diagnoses all feature quantities to identify faults in the servo all-in-one machine.

[0078] In this embodiment, in step S1, the coupled dynamics model includes:

[0079] The mathematical model of the servo motor in the dq rotating coordinate system is as follows:

[0080] [1]

[0081] in, These are the voltage components along the d-axis and q-axis, respectively. For stator resistance, , These are the stator winding flux linkages for the d-axis and q-axis, respectively. The angular frequency of the stator current rotation.

[0082] The vibration model of the cavity structure is as follows: [2]

[0083] in, For the equivalent mass of the cavity. This is the equivalent displacement in the direction of vibration. For equivalent stiffness, For equivalent damping, This is the torque-structure transmission coefficient.

[0084] The motion equation of the servo motor shaft and the cavity structure when coupled through the mounting flange, bolts, and housing is as follows:

[0085] [3]

[0086] in, For mechanical inertia, Let t be the mechanical angular velocity and t be the time. This is the load torque;

[0087] The coupled disturbance torque generated by the vibration reaction of the cavity structure is calculated using the following formula: ;

[0088] T eElectromagnetic torque can be expressed as: [4]

[0089] in, This represents the actual motor torque coefficient.

[0090] The parameters of the servo motor during operation were analyzed using a coupled dynamics model. Controlled excitation experiments were conducted on the servo motor, revealing that when the cavity structure frequency approaches its natural frequency, the cavity exhibits a significant resonance response. This resonance affects the air gap magnetic field distribution and back electromotive force waveform of the servo motor. In other words, the frequency at which the cavity structure frequency approaches its natural frequency is a specific frequency at which abnormal vibrations occur in the cavity structure. .

[0091] In this embodiment, step S2 also uses a sliding window method to buffer the acquired three-phase stator current signal. , , and three-phase stator voltage signal , , and the three-phase stator current signal , , and three-phase stator voltage signal , , Preprocessing is performed, followed by Clarke transform and Park transform.

[0092] Specifically, preprocessing includes the following steps:

[0093] First, a first-order high-pass filter is used to remove the three-phase stator current signal. , , and three-phase stator voltage signal , , Mid-to-low frequency baseline drift.

[0094] Then, the three-phase stator current signal is weighted and smoothed using a Hanning window. , , and three-phase stator voltage signal , , High-frequency noise in the medium.

[0095] Finally, the three-phase stator current signal after weighting by a first-order high-pass filter and a Hanning window is processed. , , and three-phase stator voltage signal , , Dynamic normalization is performed to eliminate the influence of current amplitude at different operating points. This is achieved by analyzing the three-phase stator current signals. , , and three-phase stator voltage signal , , Preprocessing improves the signal-to-noise ratio, significantly enhances signal quality, and increases detection accuracy and efficiency, resulting in high reliability.

[0096] The d-axis current component i is obtained through Clarke transform and Park transform. d q-axis current component i q The transformation formula is:

[0097]

[0098] Based on the d-axis and q-axis inductance L of the motor d L q and permanent magnet flux The d-axis flux linkage was calculated. and q-axis flux :

[0099] .

[0100] In this embodiment, the electromagnetic torque T of the servo motor during operation e The calculation formula is:

[0101] [5]

[0102] in, It is a differential operator.

[0103] In this embodiment, based on a specific frequency For three-phase stator current signals , , Three-phase stator voltage signal , , and electromagnetic torque T e Perform FFT transformation and processing to obtain a specific frequency. The characteristic quantities of different electrical signals specifically include:

[0104] Obtain the high-frequency current component in the three-phase stator current : [6]

[0105] in, The amplitude of the sidebands caused by the vibration of the cavity structure. This is the fundamental frequency of the servo motor. It is the phase angle of the high-frequency current component;

[0106] Perform an FFT transform on the three-phase stator current to obtain the current phase and calculate the energy ratio corresponding to the high-frequency current components. The calculation formula is:

[0107] [7];

[0108] in, This is the sum of the energy of the high-frequency components. It is the sum of all frequency components. The sampling frequency of the servo all-in-one machine. This is the dividing frequency for the servo motor, used to distinguish between the low-frequency motor fundamental frequency region and the high-frequency resonance sensitive region. Set between the "fundamental frequency of the servo motor" and the "possible cavity resonant frequency".

[0109] It should be noted that when the cavity becomes loose or resonance is enhanced, the sideband amplitude caused by the vibration of the cavity structure will increase. Increase, energy ratio It will increase significantly, and other high-frequency current components will also increase the energy ratio. An increase occurs, and formula [7] applies to The calculation includes not only the sideband amplitudes caused by the vibration of the cavity structure. This also includes other high-frequency current components, so it is used express, It serves as an intermediate variable to aid in calculations, representing the current component at the corresponding frequency.

[0110] Perform an FFT transformation on the three-phase stator voltages to obtain the voltage phase and calculate the phase difference between the voltage and current. and the phase difference with the fundamental frequency of the servo motor Subtraction to obtain phase transition values The calculation formula is:

[0111] [8];

[0112] Specifically, the phase difference between voltage and current is obtained by subtracting the current phase from the voltage phase. .

[0113] It should be noted that when the servo all-in-one machine is working normally, the phase difference between voltage and current changes smoothly with frequency; however, when the cavity structure resonates, the back electromotive force waveform is distorted due to changes in the flexibility of the cavity structure, resulting in abrupt changes in the phase difference curve. This is addressed by detecting the phase abrupt change value. The magnitude of the abrupt change can distinguish whether the cavity structure is loose or whether the cavity structure stiffness has decreased.

[0114] For electromagnetic torque T e Perform an FFT transform to obtain a specific frequency. The torque amplitude is used to calculate the equivalent index of the vibration amplitude of the cavity structure according to formula [4]. The calculation formula is:

[0115] [9]

[0116] It should be noted that the equivalent indicators When it increases, the electromagnetic torque T e The greater the fluctuation.

[0117] In this embodiment, fault identification is performed using a set threshold logic. Furthermore, the trend of abnormal vibration in the cavity structure is determined by setting a threshold (which can be obtained through calibration experiments). This method has a short judgment cycle and fast response speed, facilitating early alarm for servo all-in-one machine faults. Further, fault identification includes:

[0118] If energy ratio When the cavity structure vibrates abnormally at a specific frequency, it increases. When the frequency approaches the structure's natural frequency, the fault type is cavity resonance.

[0119] If the phase abrupt value When the specific frequency changes and the cavity structure vibrates abnormally. If unstable, the fault type is that the cavity structure has become loose;

[0120] If energy ratio and phase change value The equivalent index of the vibration amplitude of the cavity structure appears in all cases. If both increase simultaneously, the fault type is a compound fault, which is a compound fault formed by the simultaneous occurrence of two situations: resonance of the cavity and loosening of the cavity structure.

[0121] In this embodiment, adaptive tracking is also performed on specific frequencies when the cavity structure vibrates abnormally. That is, the next time step in step S4 is tracked using the recursive least squares (RLS) or extended Kalman filter (EKF) algorithm. Predicting abnormal vibrations at specific frequencies in the cavity structure involves the following steps:

[0122] Based on the vibration model of the cavity structure, the electromagnetic excitation force is calculated by back-calculating the three-phase stator current fluctuation, and the observation error is obtained. The calculation formula is: ;

[0123] in, Represents the equivalent displacement in the direction of vibration. The functional relationship with time t, based on Predicted values ​​calculated using recursive least squares or extended Kalman filtering algorithms.

[0124] Based on observation error Recursive update parameters The calculation formula is:

[0125]

[0126] in, For cavity equivalent mass The functional relationship with time t, For equivalent stiffness Functional relationship with time t For equivalent damping The functional relationship with time t, where K(t) is the gain matrix, is calculated using the following formula:

[0127]

[0128] in, Represents the prediction variance matrix. C Represents the measurement matrix. R This represents the measurement noise covariance matrix.

[0129] According to the updated parameters Real-time calculation and updating of specific frequencies when the cavity structure vibrates abnormally. The calculation formula is:

[0130] .

[0131] In this embodiment, the method further includes a self-learning mechanism, specifically including:

[0132] (1) When the servo all-in-one machine runs stably and continuously for more than a set period, and the change in the characteristic parameter value is less than 5%, then the characteristic range of the stable state is generated based on the characteristic parameter value, and the characteristic range of the stable state is saved as a new threshold template; in other words, when the servo all-in-one machine runs stably and continuously for a certain working time (such as a set time period of 8 hours), and the energy ratio is less than 5%, then the stable state characteristic range is generated based on the characteristic parameter value, and the stable state characteristic range is saved as a new threshold template; Phase abrupt change value and specific frequencies If the change is less than 5%, then the energy ratio will be... Phase abrupt change value and specific frequencies A stable state feature range is generated, which consists of the feature parameters under the stable state and their reasonable tolerance range (5%). The stable state feature range is used as a threshold template and saved. It is used to judge the trend of abnormal vibration of the cavity structure and to identify faults. It can adapt to changes in the long-term operating environment and reduce detection errors.

[0133] (2) If a slow drift in the value of the characteristic parameter is detected, the specific frequency is automatically updated when the cavity structure vibrates abnormally, so as to achieve the specific frequency. Adaptive drift compensation over operating time. When the characteristic parameter value drifts slowly, at a specific frequency... It can change continuously along a certain direction, such as a specific frequency. The threshold can be continuously increased or continuously decreased. It should be noted that each time the servo unit restarts, it will perform initialization, i.e., load the latest threshold template, to ensure detection consistency and device adaptability.

[0134] This embodiment of a servo integrated machine fault detection method constructs a coupled dynamics model and analyzes the three-phase stator current signal. , , and three-phase stator voltage signal , , Processing and extracting specific frequencies It can measure the characteristic quantities of different electrical signals without the need for external sensing devices, making it suitable for harsh working conditions such as sealed and explosion-proof environments, thus reducing the difficulty of implementation; in addition, it can measure specific frequencies. This method fuses and determines the characteristics of different electrical signals, exhibiting strong anti-interference capabilities and environmental adaptability, maintaining accurate detection under varying loads and speeds. Compared to traditional methods, this embodiment significantly improves real-time performance and implementation cost, effectively avoiding mechanical fatigue or control anomalies caused by cavity structure resonance, reducing maintenance costs, and enhancing the safety and intelligence of the servo integrated machine. It is particularly suitable for online status monitoring and health management of explosion-proof and high-reliability servo systems used in mining.

[0135] Example 2

[0136] The difference from Example 1 is that, in order to further improve the detection accuracy of fault detection, step S5 can also perform fault identification through a fault diagnosis model, specifically including:

[0137] Get the current energy ratio Phase abrupt change value and specific frequencies ;

[0138] Current energy ratio Phase abrupt change value and specific frequencies The input is fed into the fault diagnosis model for fault detection, and the detection results are obtained. The detection results include: y = 0 (normal), y = 1 (resonance occurs in the cavity), y = 2 (loosening of the cavity structure) or y = 3 (combined fault).

[0139] The fault diagnosis model is a trained SVM (Support Vector Machine) or CNN (Convolutional Neural Network) classifier.

[0140] In this embodiment, sample data such as current, voltage, and torque signals under the "normal state" and "different fault states" of the servo all-in-one machine are acquired to form a sample dataset. Furthermore, the sample data of the normal state comes from the calibration operation data of the servo all-in-one machine. The sample data of resonance, loosening, and combined faults are acquired through simulated loading, structural loosening experiments, and resonance excitation, and are repeatedly collected on the experimental bench to form a sample dataset that can be used to train an SVM or CNN classifier. The sample dataset is input into the SVM or CNN classifier for training to obtain a trained SVM or CNN classifier.

[0141] It should be noted that SVM or CNN classifiers are existing technologies, and will not be elaborated on here for the sake of brevity.

[0142] Example 3

[0143] The difference from Example 1 is that step S5 identifies faults using a set threshold logic and a fault diagnosis model, specifically including:

[0144] First, fault identification is performed using a predefined threshold logic to determine the trend of abnormal vibration in the cavity structure. When multiple abnormalities are detected consecutively, a fault diagnosis model is used for in-depth analysis. By first detecting abnormal vibration in the cavity structure using threshold detection, and then combining this with the fault diagnosis model for further fault detection, both detection efficiency and accuracy are improved.

[0145] Example 4

[0146] Existing technologies, due to resource-constrained embedded controllers, cannot achieve real-time detection and low false alarm rate judgment without affecting the main control circuit, resulting in high false alarm rates and slow diagnostic efficiency. This application also provides a servo integrated machine, such as... Figure 2 As shown, it specifically includes:

[0147] Servo all-in-one machine body 3;

[0148] And a controller 2 electrically connected to the servo all-in-one machine body 3, the controller 2 being configured to execute the servo all-in-one machine fault detection method described above.

[0149] In this embodiment, the controller 2 includes a signal acquisition unit 21, an FPGA unit 22, and an MCU unit 23;

[0150] The signal acquisition unit 21 synchronously acquires and processes the three-phase stator current signal during servo motor operation at a fixed period. , , and three-phase stator voltage signal , , ;

[0151] The processed three-phase stator current signal is processed by FPGA unit 22. , , and three-phase stator voltage signal , , Perform FFT analysis, feature extraction, and adaptive parameter tracking;

[0152] Fault identification and self-learning updates are performed through MCU unit 23.

[0153] The foregoing Figure 1 Various variations and specific examples of the servo all-in-one machine fault detection method in Embodiment 1 are also applicable to the servo all-in-one machine in this embodiment. Through the foregoing detailed description of the servo all-in-one machine fault detection method, those skilled in the art can clearly understand the implementation method of the servo all-in-one machine in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0154] The embodiments of this application can be directly integrated into the controller 2 without adding external hardware, which improves detection accuracy and detection efficiency, and further reduces the implementation difficulty.

[0155] Example 5

[0156] This application provides a computer device including a processor and a memory. The memory stores at least one instruction or at least one program, which is loaded and executed by the processor to implement a rolling bearing fault intelligent diagnosis method as provided in the above method embodiments.

[0157] Figure 3This diagram illustrates a hardware structure of an apparatus for implementing an intelligent diagnostic method for rolling bearing faults provided in an embodiment of this application. The apparatus may constitute or include the device or system provided in the embodiment of this application. Figure 3 As shown, the computer device 10 may include one or more processors 1002 (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 1004 for storing data, and a transmission device 1006 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 3 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer device 10 may also include... Figure 3 The more or fewer components shown, or having the same Figure 3 The different configurations shown.

[0158] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuit may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer device 10 (or mobile device). As involved in the embodiments of this application, the data processing circuit serves as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0159] The memory 1004 can be used to store software programs and modules for application software, such as the program instructions / data storage device corresponding to the intelligent diagnosis method for rolling bearing faults in this embodiment of the application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, thereby implementing the aforementioned method. The memory 1004 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1004 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer device 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0160] The transmission device 1006 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer device 10. In one example, the transmission device 1006 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 1006 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0161] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer device 10 (or mobile device).

[0162] Example 6

[0163] This application embodiment also provides a computer-readable storage medium, which can be disposed in a server to store at least one instruction or at least one program related to implementing a rolling bearing fault intelligent diagnosis method in the method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the rolling bearing fault intelligent diagnosis method provided in the above method embodiment.

[0164] Optionally, in this embodiment, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0165] Example 7

[0166] This invention also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform a rolling bearing fault intelligent diagnosis method provided in the various optional embodiments described above.

[0167] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0168] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device, equipment, and storage medium embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0169] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0170] Based on the above-described preferred embodiments of the present invention, and through the foregoing description, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A fault detection method for a servo all-in-one machine, characterized in that, The method includes the following steps: S1, Construct a coupled dynamic model of the servo motor and the cavity structure; The coupled dynamics model includes: The mathematical model of the servo motor in the dq rotating coordinate system is as follows: [1] in, These are the voltage components along the d-axis and q-axis, respectively. For stator resistance, , These are the stator winding flux linkages for the d-axis and q-axis, respectively. The angular frequency of the stator current rotation; The vibration model of the cavity structure is as follows: [2] in, For the equivalent mass of the cavity. This is the equivalent displacement in the direction of vibration. For equivalent stiffness, For equivalent damping, This is the torque-structure transmission coefficient; The motion equation of the servo motor shaft coupled to the cavity structure via mounting flange, bolts, and housing is as follows: [3] in, For mechanical inertia, Let t be the mechanical angular velocity and t be the time. For load torque, The coupled disturbance torque generated by the vibration reaction of the cavity structure is calculated using the following formula: ; Electromagnetic torque can be expressed as: [4] in, This is the actual motor torque coefficient; S2, Acquires the three-phase stator current signal during servo motor operation. , , and three-phase stator voltage signal , , The d-axis current component i is obtained through Clarke transform and Park transform. d and q-axis current component i q ; S3, calculate the electromagnetic torque T of the servo motor during operation using the motor's electromagnetic equations. e ; S4, Obtain the frequency of abnormal vibration of the cavity structure through a coupled dynamics model. Based on the frequency For three-phase stator current signals , , Three-phase stator voltage signal , , and electromagnetic torque T e Perform FFT transformation and processing to obtain the frequency. Characteristic quantities of different electrical signals; S5 normalizes and diagnoses all feature quantities to identify faults in the servo all-in-one machine.

2. The servo all-in-one machine fault detection method as described in claim 1, characterized in that, The electromagnetic torque T of the servo motor during operation e The calculation formula is: [5] in, It is a differential operator.

3. The servo all-in-one machine fault detection method as described in claim 2, characterized in that, Based on the frequency For three-phase stator current signals , , Three-phase stator voltage signal , , and electromagnetic torque T e Perform FFT transformation and processing to obtain the frequency. The characteristic quantities of different electrical signals specifically include: Obtain the high-frequency current component in the three-phase stator current : [6] in, The amplitude of the sidebands caused by the vibration of the cavity structure. This is the fundamental frequency of the servo motor. It is the phase angle of the high-frequency current component; Perform an FFT transformation on the three-phase stator current to calculate the energy ratio corresponding to the high-frequency current component. The calculation formula is: [7] in, This is the sum of the energy of the high-frequency components. It is the sum of all frequency components. The sampling frequency of the servo all-in-one machine. The dividing frequency for the servo all-in-one machine This refers to the current component at the corresponding frequency. Perform an FFT transformation on the three-phase stator voltages to obtain the voltage phase and calculate the phase difference between the voltage and current. and the phase difference with the fundamental frequency of the servo motor Subtraction to obtain phase transition values The calculation formula is: [8]； For the electromagnetic torque T e Perform an FFT transform to obtain the frequency. The torque amplitude is used to calculate the equivalent index of the vibration amplitude of the cavity structure according to formula [4]. The calculation formula is: [9]。 4. The servo all-in-one machine fault detection method as described in claim 3, characterized in that, Step S5 involves fault identification through a set threshold logic and / or through a fault diagnosis model. Fault identification includes: If energy ratio When the frequency increases and the cavity structure vibrates abnormally When the frequency approaches the structure's natural frequency, the fault type is cavity resonance. If the phase abrupt value Frequency changes and abnormal vibration of cavity structure If unstable, the fault type is that the cavity structure has become loose; If energy ratio and phase change value The equivalent index of the vibration amplitude of the cavity structure appears in all cases. If both increase simultaneously, the fault type is a compound fault.

5. The servo all-in-one machine fault detection method as described in claim 4, characterized in that, In step S4, adaptive tracking of the frequency when the cavity structure vibrates abnormally is also performed, specifically including the following steps: Based on the vibration model of the cavity structure, the electromagnetic excitation force is calculated by back-calculating the three-phase stator current fluctuation, and the observation error is obtained. The calculation formula is: in, Represents the equivalent displacement in the direction of vibration. The functional relationship with time t, based on Predicted values ​​calculated using recursive least squares or extended Kalman filter algorithms; Based on observation error Recursive update parameters The calculation formula is: in, For cavity equivalent mass The functional relationship with time t, For equivalent stiffness Functional relationship with time t For equivalent damping The functional relationship between time t and K(t) is the gain matrix; According to the updated parameters Real-time calculation and updating of the frequency of abnormal vibration of the cavity structure The calculation formula is: 。 6. The servo all-in-one machine fault detection method as described in claim 3, characterized in that, The method also includes a self-learning mechanism, specifically including: When the servo all-in-one machine runs continuously and stably for more than the set period, and the change of the characteristic parameter value is less than 5%, the characteristic range of the stable state is generated according to the characteristic parameter value, and the characteristic range of the stable state is saved as a new threshold template. If a slow drift in the value of a characteristic parameter is detected, the frequency will be automatically updated when the cavity structure vibrates abnormally.

7. The servo all-in-one machine fault detection method as described in claim 1, characterized in that, Step S2 includes buffering the acquired three-phase stator current signal using a sliding window method. , , and three-phase stator voltage signal , , and the three-phase stator current signal , , and three-phase stator voltage signal , , Preprocessing is performed.

8. A servo all-in-one machine, characterized in that, include: Servo all-in-one machine body (3); And a controller (2) electrically connected to the servo all-in-one machine body (3), the controller (2) being configured to perform the servo all-in-one machine fault detection method as described in any one of claims 1 to 7.

9. A servo all-in-one machine as described in claim 8, characterized in that, The controller (2) includes a signal acquisition unit (21), an FPGA unit (22), and an MCU unit (23). The three-phase stator current signal of the servo motor during operation is synchronously acquired and processed at a fixed period by the signal acquisition unit (21). , , and three-phase stator voltage signal , , ; The processed three-phase stator current signal is processed by the FPGA unit (22). , , and three-phase stator voltage signal , , Perform FFT analysis, feature extraction, and adaptive parameter tracking; Fault identification and self-learning updates are performed through the MCU unit (23).

Images