Fault diagnosis method for permanent magnet synchronous motor drive based on fault classifier

Abstract

The present invention belongs to the field of motor testing technology, and is specifically a permanent magnet synchronous motor driver fault diagnosis method based on a fault classifier. The method comprises the following steps: obtaining operating environment data of the environment in which the permanent magnet synchronous motor driver is located within a diagnosis cycle, and determining whether the operating environment of the permanent magnet synchronous motor driver is normal; if the operating environment is abnormal, obtaining real-time operating data of the permanent magnet synchronous motor driver, and inputting the real-time operating data into a fault classifier pre-stored in a database; if the operating environment is normal, evaluating the instruction completion status of the permanent magnet synchronous motor driver, and determining whether the instruction completion status of the permanent magnet synchronous motor driver is normal; if the instruction completion status is normal, obtaining real-time operating data of the permanent magnet synchronous motor driver, and determining whether the operating state of the permanent magnet synchronous motor driver is normal. The present invention improves the efficiency and accuracy of fault diagnosis, and helps to take corresponding maintenance or repair measures in a timely manner.

Description

Technical Field

[0001] The present invention belongs to the technical field of motor testing, and in particular relates to a permanent magnet synchronous motor driver fault diagnosis method based on a fault classifier. Background Art

[0002] Permanent magnet synchronous motors (PMSMs) offer advantages such as compact size, high power density, and high efficiency, making them widely used in AC speed control systems. Condition monitoring and fault diagnosis technologies, enabling preventive maintenance of motor drives (inverters), have also garnered significant attention. Motor drives are susceptible to many different types of faults, including stator faults, rotor faults, mechanical faults, sensor faults, and power switching device faults. Fault diagnosis of PMSM drives involves detecting and identifying various potential motor faults, including winding faults, bearing damage, and broken rotor bars. These faults can impact the efficiency and performance of the motor drive and may even cause the motor to shut down.

[0003] Some existing permanent magnet synchronous motor drive fault diagnosis technologies have the problem of difficulty in combining operating environment data and real-time operating data to quickly and accurately diagnose permanent magnet synchronous motor drive faults in complex and changing operating environments. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention provides a permanent magnet synchronous motor drive fault diagnosis method based on a fault classifier, which can effectively distinguish between environmental anomalies, instruction execution anomalies and abnormal operating status of the motor itself, thereby achieving accurate judgment of the motor fault type.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0006] The permanent magnet synchronous motor drive fault diagnosis method based on the fault classifier includes the following steps:

[0007] During a diagnostic cycle, the operating environment data of the permanent magnet synchronous motor drive's environment is obtained. Based on the operating environment data, it is determined whether the permanent magnet synchronous motor drive's operating environment is normal. The operating environment data includes ambient temperature, electromagnetic interference level, and power supply stability:

[0008] If the operating environment is abnormal, the real-time operating data of the permanent magnet synchronous motor drive is obtained and input into the fault classifier pre-stored in the database. The real-time operating data includes the motor winding impedance, circuit harmonic content, DC link voltage and rotor offset.

[0009] If the operating environment is normal, evaluate the instruction completion status of the permanent magnet synchronous motor driver to determine whether the instruction completion status of the permanent magnet synchronous motor driver is normal:

[0010] If the instruction completion is abnormal, the real-time operation data of the permanent magnet synchronous motor driver is obtained and the real-time operation data is input into a fault classifier pre-stored in the database;

[0011] If the command is completed normally, the real-time operation data of the permanent magnet synchronous motor driver is obtained, and based on the real-time operation data, it is determined whether the operation status of the permanent magnet synchronous motor driver is normal:

[0012] If the operating status is normal, enter the next diagnostic cycle;

[0013] If the operating state is abnormal, real-time operating data of the permanent magnet synchronous motor driver is obtained and the real-time operating data is input into a fault classifier pre-stored in the database;

[0014] The fault classifier pre-stored in the database diagnoses the real-time operation data to determine the fault type of the permanent magnet synchronous motor drive.

[0015] Preferably, judging whether the operating environment of the permanent magnet synchronous motor driver is normal based on the operating environment data includes the following steps:

[0016] Obtain operating environment parameter data stored in the database, including ambient temperature, electromagnetic interference level, and power supply stability;

[0017] The operating environment data is integrated and analyzed with the operating environment parameter data to obtain the operating environment evaluation index;

[0018] Determine whether the operating environment assessment value is greater than the operating environment assessment threshold stored in the database:

[0019] If the operating environment evaluation value is greater than the operating environment evaluation threshold stored in the database, the operating environment is abnormal;

[0020] If the operating environment evaluation value is not greater than the operating environment evaluation threshold stored in the database, the operating environment is normal.

[0021] Preferably, the method for obtaining the operating environment evaluation value is as follows:

[0022] ;

[0023] Where, Yp is the operating environment assessment value, WsH is the ambient temperature, Ds is the electromagnetic interference level, Ws is the power supply stability, WcH is the ambient parameter temperature, Dc is the parameter electromagnetic interference level, and Wc is the parameter power supply stability.

[0024] Preferably, evaluating the instruction completion status of the permanent magnet synchronous motor driver to determine whether the instruction completion status of the permanent magnet synchronous motor driver is normal includes the following steps:

[0025] Obtain command completion data for permanent magnet synchronous motor drivers, including average command response time, dynamic response time, and steady-state achievement time.

[0026] Obtain instruction completion parameter data stored in the database, including instruction parameter average response time, parameter dynamic response time, and parameter steady-state achievement time;

[0027] Obtain the allowable deviation data of the instruction completion status, including the allowable deviation value of the dynamic response time and the allowable deviation value of the steady-state achievement time;

[0028] Obtaining an instruction completion status evaluation value based on instruction completion status data, instruction completion status parameter data, and instruction completion status allowable deviation data;

[0029] Determine whether the instruction completion evaluation value is greater than the instruction completion evaluation threshold stored in the database:

[0030] If the instruction completion evaluation value is greater than the instruction completion evaluation threshold stored in the database, the instruction completion status is abnormal;

[0031] If the instruction completion status evaluation value is not greater than the instruction completion status evaluation threshold stored in the database, the instruction completion status is normal.

[0032] Preferably, obtaining instruction completion status allowable deviation data includes the following steps:

[0033] Based on the device information of the permanent magnet synchronous motor drive, a matching data set is obtained from the database. The matching data set includes multiple deviation value matching data. The deviation value matching data includes an electromagnetic interference matching value, a power supply stability matching value, and a daily average temperature of the drive.

[0034] Obtain the data to be matched for the permanent magnet synchronous motor drive, including electromagnetic interference level, power supply stability, and actual drive temperature;

[0035] Compare the data to be matched with each deviation value matching data one by one, and determine the deviation value matching data closest to the data to be matched;

[0036] The instruction completion status allowable deviation data corresponding to the deviation value matching data stored in the database is obtained.

[0037] Preferably, comparing the data to be matched with each deviation value matching data one by one to determine the deviation value matching data closest to the data to be matched comprises the following steps:

[0038] Obtaining matching values ​​after comparing the data to be matched with the matching data of each deviation value;

[0039] Determine the minimum matching value;

[0040] The deviation value matching data corresponding to the minimum matching value is output as the deviation value matching data closest to the data to be matched.

[0041] Preferably, the method for obtaining the matching value is as follows:

[0042] ;

[0043] Where PP is the matching value, Ds is the electromagnetic interference level, Ws is the power supply stability, Qsw is the actual temperature of the driver, Dp is the electromagnetic interference matching value, Wp is the power supply stability matching value, Qcw is the average daily temperature of the driver, e is a natural constant, and ln is a logarithmic function, which represents the logarithm with base e.

[0044] Preferably, judging whether the operating state of the permanent magnet synchronous motor driver is normal based on the real-time operating data includes the following steps:

[0045] Obtain the operating status parameter data of the permanent magnet synchronous motor drive stored in the database, including the motor winding parameter impedance, parameter circuit harmonic content, DC link parameter voltage and rotor parameter offset;

[0046] Obtaining the allowable deviation data of the operating status, including the allowable deviation value of the motor winding parameter impedance and the allowable deviation value of the DC link parameter voltage;

[0047] The operating status of the permanent magnet synchronous motor drive is evaluated based on real-time operating data, operating status parameter data and operating status allowable deviation data to determine whether the operating status is normal.

[0048] Preferably, evaluating the operating state of the permanent magnet synchronous motor driver based on the real-time operating data, the operating state parameter data, and the operating state allowable deviation data to determine whether the operating state is normal includes the following steps:

[0049] Obtaining an operating status evaluation index based on real-time operating data, operating status parameter data, and operating status allowable deviation data;

[0050] Determine whether the running status evaluation index is greater than the running status evaluation threshold stored in the database:

[0051] If the running status evaluation index is greater than the running status evaluation threshold stored in the database, the running status is abnormal;

[0052] If the running status evaluation index is not greater than the running status evaluation threshold stored in the database, the running status is normal.

[0053] Preferably, obtaining the operating state allowable deviation data includes the following steps:

[0054] Obtain operating status matching data for permanent magnet synchronous motor drives, including the average daily continuous use time of the drive, electromagnetic interference level, and power supply stability;

[0055] Compare the operating status matching data with each state deviation matching data stored in the database one by one to obtain the comparison coefficient. The state deviation matching data includes the matching parameters of the average daily continuous use time of the drive, the electromagnetic interference level matching parameters, and the power supply stability matching parameters.

[0056] Determine the minimum comparison coefficient and extract the operating state allowable deviation data corresponding to the minimum comparison coefficient from the database.

[0057] The present invention has the following beneficial effects:

[0058] The present invention monitors operating environment data and real-time operating data and uses pre-stored fault classifiers for analysis. This method can effectively distinguish between environmental anomalies, instruction execution anomalies, and abnormal operating status of the motor itself, thereby achieving accurate judgment of the type of motor fault. It solves the technical problem of quickly and accurately diagnosing permanent magnet synchronous motor drive faults in complex and changing operating environments. It not only improves the efficiency and accuracy of fault diagnosis, but also helps to take corresponding maintenance or repair measures in a timely manner, reducing downtime and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 is a flow chart of the method of the present invention;

[0060] Figure 2 This is a flowchart of the JITGP-ELM method framework in an embodiment of the present invention;

[0061] Figure 3 Schematic diagram of the network structure of the extreme learning machine in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The embodiments of the present invention are further described below with reference to the accompanying drawings:

[0063] This embodiment uses a permanent magnet synchronous motor driver fault diagnosis method based on a fault classifier to first determine whether the operating environment of the motor driver is normal, and the factors considered include ambient temperature, electromagnetic interference level and power supply stability. This step is fundamental because environmental factors often have a significant impact on the normal operation of the equipment. If the environment is abnormal, it directly enters the stage of obtaining the real-time operating data of the motor, such as motor winding impedance, circuit harmonic content, etc., to determine the type of fault. If the environment is normal, it checks whether the command completion of the motor driver meets expectations. Based on the real-time operating data and command completion of the motor, it is determined whether the operating status of the motor is normal. If any abnormal state is found, the real-time data is input into a pre-set fault classifier for analysis to diagnose the specific fault type.

[0064] like Figure 1 As shown, a fault diagnosis method for a permanent magnet synchronous motor drive based on a fault classifier includes the following steps: within a diagnosis cycle, obtaining operating environment data of the environment in which the permanent magnet synchronous motor drive is located, the operating environment data including ambient temperature (using a thermistor, thermocouple, or infrared sensor to monitor the ambient temperature. These sensors can accurately measure the temperature of the drive and its surroundings and transmit the data to a monitoring system in real time. The thermistor can be a PT100 or NTC thermistor), electromagnetic interference level (using a specialized electromagnetic interference detection device, such as a spectrum analyzer, to measure the electromagnetic noise level in the environment), and power supply stability (using a voltage sensor and a current sensor to monitor the voltage or current stability of the power supply line, such as the voltage mean square deviation or the current mean square deviation). Based on the operating environment data, determining whether the operating environment of the permanent magnet synchronous motor drive is normal includes the following steps:

[0065] First, real-time operating data of the environment in which the permanent magnet synchronous motor drive is located is collected, and the outputs of all sensors are connected to a data acquisition system. The system is responsible for collecting, storing and preprocessing data, and using appropriate communication protocols (such as Modbus, CAN bus or Ethernet) to send the collected data to the central control system or cloud platform for further analysis and processing. Then, the operating environment parameter data stored in the database is obtained. The operating environment parameter data includes the ambient parameter temperature, the parameter electromagnetic interference level and the parameter power supply stability; the operating environment data is integrated and analyzed with the operating environment parameter data to obtain the operating environment evaluation index; it is determined whether the operating environment evaluation value is greater than the operating environment evaluation threshold stored in the database: if the operating environment evaluation value is greater than the operating environment evaluation threshold stored in the database, the operating environment is abnormal; if the operating environment evaluation value is not greater than the operating environment evaluation threshold stored in the database, the operating environment is normal.

[0066] Promptly identifying adverse operating conditions, such as excessive temperatures, excessive electromagnetic interference, or unstable power supply, can negatively impact motor performance. Early identification and response can prevent potential failures or damage, potentially leading to more serious consequences.

[0067] The method for obtaining the operating environment evaluation value is as follows:

[0068] ;

[0069] Where Yp is the operating environment assessment value, WsH is the ambient temperature, Ds is the electromagnetic interference level, Ws is the power supply stability, WcH is the reference ambient temperature, Dc is the reference electromagnetic interference level, and Wc is the reference power supply stability. This formula is designed to evaluate the operating environment quality of permanent magnet synchronous motor drives, comprehensively considering three key factors: ambient temperature, electromagnetic interference level, and power supply stability. Each parameter directly affects the performance and lifespan of the motor, so a comprehensive assessment of these parameters is crucial to ensuring reliable motor operation.

[0070] Ambient temperature has a direct impact on the thermal state of the motor. High temperatures can cause the motor to overheat, affecting insulation performance and increasing the risk of failure. Therefore, monitoring the temperature difference from the reference standard is crucial. Electromagnetic interference can affect the normal operation of electronic equipment in the motor drive system, such as the control system's microprocessor and other sensitive electronic components. Therefore, assessing the ratio of actual interference to DC is key to determining whether the environment is suitable for normal operation. Power supply stability directly affects the performance and safety of the motor. Power supply fluctuations can cause abnormal operation or damage to the motor control system, so monitoring the ratio of actual power supply stability to the reference power supply stability is essential. Using a combination of absolute value differences and ratios, this design aims to quantify the specific contribution of each parameter to environmental adaptability and ensure that significant deviations from any one parameter are captured and reflected in the overall assessment value.

[0071] By comparing real-time data to pre-set standards, this approach provides a quantitative and precise way to assess the environment in which the motor is operating. This precise matching ensures operation under ideal conditions, thereby increasing the efficiency and lifespan of the equipment.

[0072] If the operating environment is abnormal, the real-time operating data of the permanent magnet synchronous motor driver is obtained and input into the fault classifier pre-stored in the database. The real-time operating data includes the motor winding impedance, circuit harmonic content, DC link voltage and rotor offset. If the operating environment is normal, the instruction completion status of the permanent magnet synchronous motor driver is evaluated to determine whether the instruction completion status of the permanent magnet synchronous motor driver is normal. By comparing the actual instruction response time with the set standard, it can be confirmed whether the motor driver is operating normally within the designed performance parameter range.

[0073] Obtain instruction completion status data of the permanent magnet synchronous motor driver, which includes the average instruction response time (the average time required for the motor driver to start executing the instruction after receiving the instruction), the dynamic response time (the time it takes for the motor to accelerate to reach the target state, the target state is to reach the set speed or position, etc.), and the steady-state achievement time (the time required for the motor to stabilize in the target state after reaching the target state); obtain instruction completion status parameter data stored in the database, which includes the instruction parameter average response time, parameter dynamic response time, and parameter steady-state achievement time. These data are determined based on performance tests, manufacturer specifications, or empirical standards, and provide a benchmark for evaluating whether the current system performance is within an acceptable range.

[0074] Capturing the command completion tolerance data defines the acceptable deviation range for dynamic response time and steady-state time. This is important because in actual operation, various factors (such as load changes and power supply fluctuations) may cause slight performance fluctuations. The command completion tolerance data includes the dynamic response time tolerance and the steady-state time tolerance.

[0075] Based on the device information of the permanent magnet synchronous motor drive, a matching dataset is retrieved from the database. The matching dataset includes multiple deviation value matching data, including electromagnetic interference matching values, power supply stability matching values, and the daily average temperature of the drive. The matching data to be matched is also retrieved for the permanent magnet synchronous motor drive. The matching data to be matched includes electromagnetic interference level (EMI) (EMI can interfere with the drive's control system, particularly affecting sensor readings and the communication bus. This interference can lead to misjudgment or delayed processing of control signals, which in turn affects dynamic response time. High EMI levels can cause transient errors in the control system, affecting the device's ability to reach steady state), power supply stability (unstable power supply can cause power supply fluctuations in the motor, which not only affects the motor's startup and acceleration processes but also causes fluctuations when attempting to reach a stable operating state, thereby extending dynamic response time and the time it takes to reach steady state), and actual drive temperature (increased temperature can affect the performance of the motor's internal insulation material, reducing motor efficiency and increasing resistance, thereby affecting the motor's response time and stability. At high temperatures, the drive may take longer to reach a stable operating state because factors such as thermal expansion can affect the operation of mechanical components). By monitoring these parameters, the actual performance of the permanent magnet synchronous motor drive under specific environmental and power supply conditions can be better understood. This helps set more realistic and feasible performance benchmarks, such as the allowable deviation values ​​for dynamic response time and steady-state achievement time.

[0076] The data to be matched is compared with each deviation value matching data one by one to determine the deviation value matching data closest to the data to be matched; and the instruction completion status allowable deviation data corresponding to the deviation value matching data stored in the database is obtained.

[0077] Determining the deviation matching data closest to the data to be matched includes the following steps: obtaining matching values ​​after comparing the data to be matched with each deviation matching data; determining the minimum matching value and selecting the historical data point that is most similar to the current condition (i.e., the minimum matching value). This indicates that the motor's performance and response under similar conditions are known and can be predicted and evaluated; outputting the deviation matching data corresponding to the minimum matching value as the deviation matching data closest to the data to be matched, and using this as a basis for predicting the current performance condition or performing fault diagnosis.

[0078] The matching value is obtained as follows:

[0079] ;

[0080] Where PP is the matching value, Ds is the electromagnetic interference level, Ws is the power supply stability, Qsw is the actual temperature of the driver, Dp is the electromagnetic interference matching value, Wp is the power supply stability matching value, Qcw is the average daily temperature of the driver, e is a natural constant, and ln is a logarithmic function, which represents the logarithm with base e.

[0081] For example, Ds = 0.5dB, Ws is expressed as voltage standard deviation, which is 2.5V, and Qsw = 25°C. The following table shows the matching values ​​of three sets of deviation matching data and the data to be matched:

[0082] Table 1 Matching values ​​of three sets of deviation matching data and data to be matched

[0083]

[0084] It can be seen from the data table that the third set of deviation matching data has the smallest matching value.

[0085] Use absolute difference and , calculate the difference between electromagnetic interference and power supply stability respectively. The absolute value difference emphasizes the direct deviation between the two quantities, whether positive or negative. Temperature difference A natural logarithm function is used for processing, with the addition of one ensuring that the logarithm function is always positive, preventing calculation errors or meaningless results. An exponential function based on a natural constant is used to account for the combined deviations from electromagnetic interference and power supply stability, minimizing the impact of deviation changes on the final matching value, ensuring that even small changes can significantly affect the results. Temperature differences are processed using logarithmic operations, smoothing their impact on the matching value and preventing temperature anomalies from excessively influencing the overall matching result.

[0086] Obtain an instruction completion status evaluation value based on instruction completion status data, instruction completion status parameter data and instruction completion status allowable deviation data; determine whether the instruction completion status evaluation value is greater than the instruction completion status evaluation threshold stored in the database: if the instruction completion status evaluation value is greater than the instruction completion status evaluation threshold stored in the database, the instruction completion status is abnormal; if the instruction completion status evaluation value is not greater than the instruction completion status evaluation threshold stored in the database, the instruction completion status is normal.

[0087] The method for obtaining the instruction completion evaluation value is as follows:

[0088] ;

[0089] Where Zp is the instruction completion evaluation value, Tsp is the average instruction response time, Tsd is the dynamic response time, Tsw is the steady-state achievement time, Tcp is the instruction parameter average response time, Tcd is the parameter dynamic response time, and Tcw is the parameter steady-state achievement time. is the allowable deviation value of dynamic response time, It is the allowable deviation value of the time to reach steady state.

[0090] The formula for calculating the command completion evaluation value incorporates key performance indicators to assess the response efficiency and stability of a permanent magnet synchronous motor drive. This formula considers three key parameters: average command response time, dynamic response time, and steady-state time. These parameters are compared against their respective set values, taking into account the corresponding tolerances. Compare the actual average response time with the set average response time. The smaller Tsp is, the faster the response speed is.

[0091] Taking into account the combination of differences and deviations, if the dynamic response time is too fast, it may mean that the system changes state quickly after receiving the command, which may cause greater stress and load on mechanical parts, electronic components and software processing. This may reduce the service life and reliability of the equipment in the long run. Excessively long response time will affect production efficiency, especially in high-speed production lines or operating environments that require quick response. Response delays may cause the production process to slow down or stagnate. Reaching steady state too quickly may mean that the system does not have enough time to make appropriate adjustments, which may lead to insufficient system stability, such as large fluctuations or adjustment requirements after reaching steady state. If it takes too long to reach steady state, the system may be in a non-optimal working state for a long time, reducing operational efficiency and output.

[0092] If the instruction completion is abnormal, real-time operating data of the permanent magnet synchronous motor driver is obtained, and the real-time operating data is input into a fault classifier pre-stored in the database; if the instruction completion is normal, real-time operating data of the permanent magnet synchronous motor driver is obtained, and whether the operating state of the permanent magnet synchronous motor driver is normal is determined based on the real-time operating data, including the following steps:

[0093] Obtain the operating status parameter data of the permanent magnet synchronous motor drive stored in the database. The operating status parameter data includes the motor winding parameter impedance (the motor winding impedance is usually measured by a resistance tester or a motor test system. These devices can calculate the impedance by injecting a known current into the motor winding when the motor is running or stopped, and then measuring the voltage response of the motor winding), the parameter circuit harmonic content (the circuit harmonic content refers to the presence of non-fundamental frequency components in the power circuit. It is measured by a harmonic analyzer or a power quality analyzer. These devices can continuously monitor the voltage and current of the power system, thereby detecting and recording the circuit harmonic level in real time), the DC link parameter voltage (the DC link voltage usually refers to the voltage level of the DC side in the motor drive. This parameter can be directly measured by a voltage sensor installed in the motor control system), and the rotor parameter offset (the rotor offset refers to the position offset of the rotor relative to its theoretical center axis. A photoelectric sensor or a magnetic sensor is used to directly monitor the rotor position).

[0094] The allowable deviation data of the operating status is obtained. The allowable deviation data of the operating status includes the allowable deviation value of the motor winding parameter impedance and the allowable deviation value of the DC link parameter voltage. These deviation values ​​take into account normal fluctuations or subtle changes that may occur in actual operation.

[0095] Obtain operating status matching data for the permanent magnet synchronous motor drive. This data includes the average daily continuous usage time of the drive (continuous and long-term use will cause the motor temperature to rise, affecting the resistance of the motor winding. Resistance increases with temperature, which requires adjustment of the allowable impedance deviation value to accommodate higher operating temperatures), electromagnetic interference level (high electromagnetic interference level may affect the signal processing of the motor control system, resulting in measurement errors and unstable operation. In high-interference environments, the impedance measurement of the motor winding may be affected, and the allowable deviation needs to be adjusted to accommodate these conditions), and power supply stability (power supply instability will cause input voltage fluctuations, which will directly affect the stability of the DC link voltage. Voltage fluctuations may cause instability in the internal current of the motor, which in turn affects the stability of the winding impedance. Therefore, power supply stability needs to be considered when designing the allowable deviation of the motor winding impedance and DC link voltage).

[0096] The operating status matching data is compared one by one with each state deviation matching data stored in the database to obtain the comparison coefficient. The state deviation matching data includes the drive's average daily continuous usage time matching parameters, electromagnetic interference level matching parameters, and power supply stability matching parameters; the minimum comparison coefficient is determined, and the operating status allowable deviation data corresponding to the minimum comparison coefficient is extracted from the database.

[0097] The method for obtaining the comparison coefficient is:

[0098] ;

[0099] Where i is the number of the state deviation matching data, is the i-th comparison coefficient, is the average daily continuous use time of the drive, Matching parameters for the average daily continuous use time of the i-th drive, is the i-th electromagnetic interference level matching parameter, is the i-th power supply stability matching parameter.

[0100] The operating status of the permanent magnet synchronous motor drive is evaluated based on real-time operating data, operating status parameter data and operating status allowable deviation data to determine whether the operating status is normal.

[0101] Obtain an operation status evaluation index based on real-time operation data, operation status parameter data and operation status allowable deviation data; determine whether the operation status evaluation index is greater than the operation status evaluation threshold stored in the database: if the operation status evaluation index is greater than the operation status evaluation threshold stored in the database, the operation status is abnormal; if the operation status evaluation index is not greater than the operation status evaluation threshold stored in the database, the operation status is normal.

[0102] The method for obtaining the operating status evaluation index is as follows:

[0103] ;

[0104] Where, YzP is the operating status evaluation index, Rsc is the motor winding impedance, Dsx is the circuit harmonic content, Rsd is the DC link voltage, Dsp is the rotor offset, Rcc is the motor winding parameter impedance, Dcx is the parameter circuit harmonic content, Rcd is the DC link parameter voltage, and Dcp is the rotor parameter offset. The allowable deviation value of the motor winding impedance parameter is determined. It is the allowable deviation value of DC link parameter voltage.

[0105] Changes in impedance can indicate electrical problems in the motor windings, such as insulation damage, poor contact, or overheating. Impedance measurements reflect the integrity and efficiency of the motor's internal electrical circuit. Harmonic content reflects power supply quality and the tolerance of the motor's electrical system. High harmonic levels can lead to reduced motor efficiency, increased heat generation, and shortened lifespan, making them a crucial indicator of motor operating quality.

[0106] The stability of the DC link voltage directly impacts the performance of the motor drive. Voltage fluctuations can cause instability in the motor control system, affecting its response speed and accuracy. Rotor position accuracy directly affects the motor's operating efficiency and mechanical wear. Rotor misalignment can cause mechanical vibration and increase bearing loads, reducing the motor's operating efficiency and lifespan.

[0107] Changes in motor winding impedance can affect motor power consumption and heat generation, thereby impacting DC link voltage stability. Furthermore, high harmonic content in the power supply can further exacerbate thermal stress in the windings and increase impedance variations. These parameters work together to provide a comprehensive reflection of the motor's overall electrical and mechanical health. For example, increased rotor misalignment can cause changes in winding impedance, as changes in mechanical position can affect electrical characteristics.

[0108] and This index reflects the degree of deviation between actual operating conditions and established standards. The use of a logarithmic function smooths out large deviations, preventing extreme values ​​from excessively impacting the evaluation results, making the evaluation index more robust and reliable. Comprehensive analysis of these parameters provides a comprehensive picture of the motor's operating status, enabling the timely identification of potential electrical and mechanical issues. This approach not only improves the accuracy of fault diagnosis but also facilitates the development of more effective maintenance strategies, ensuring the reliability and long-term stable operation of the motor system. This systematic analysis approach makes motor maintenance and monitoring more scientific and efficient, helping to reduce unplanned downtime and improve production efficiency.

[0109] If the operating status is normal, the next diagnostic cycle is entered; if the operating status is abnormal, the real-time operating data of the permanent magnet synchronous motor driver is obtained and the real-time operating data is input into the fault classifier pre-stored in the database; the fault classifier pre-stored in the database diagnoses the real-time operating data to determine the fault type of the permanent magnet synchronous motor driver.

[0110] The fault classifiers stored in the database are built based on just-in-time learning (JITL), such as Figure 2As shown in the figure, in the proposed fault diagnosis framework, an instantaneous Gaussian process is used to build a model of the healthy system, predicting its behavior. This residual is then compared with the faulty system's behavior to form a fault signature. These residuals serve as fault signatures in subsequent steps. This process is known as fault signature extraction based on an instantaneous Gaussian process. In this instantaneous Gaussian process, a Gaussian process (GP) is used to build a local model for instantaneous learning. Because instantaneous learning involves a sample selection step, the computational cost of Gaussian process modeling can be significantly reduced within the instantaneous learning framework.

[0111] As a popular local learning method, just-in-time learning (JITGP) has the advantage of low computational cost. However, when there are few samples, traditional just-in-time learning based on linear local models can be sensitive to noise, resulting in a conflict between speed and accuracy in practical applications. An improved algorithm is the Just-in-Time Gaussian Process (JITGP), whose local model is constructed using a Gaussian process model, replacing the traditional linear model. Compared to traditional just-in-time learning algorithms, JITGP has the advantages of smoothness and noise resistance, while inheriting the low computational cost and online adaptability of traditional just-in-time learning. In addition, the GP model can also provide prediction variance to reflect the probability information of the prediction.

[0112] 1) Instant Gaussian process modeling

[0113] In the instantaneous Gaussian process, the instantaneous local model is modeled by Gaussian process regression. The Gaussian process model is a non-parametric model in Bayesian statistics. The system modeling of the Gaussian process model includes the following three stages:

[0114] 11) Gaussian process prior model

[0115] As a common type of function prior, the Gaussian process model assumes At any point x is a random variable ,in and are independent constants. Therefore, the joint multivariate Gaussian distribution over a set of variables can be expressed as ,..., ,in is a matrix, N is the number of samples, It can be expressed as represent and The variance between and represent any two variables, is the covariance function, which is commonly expressed as:

[0116] (1);

[0117] Where D is the dimension of variable x, parameter Describe each dimension of x for the importance of is the scale parameter. For an unknown function , ,in is a variance of White noise, that is ,So ,..., , , which follows the Gaussian process prior framework, where if but ,otherwise .

[0118] 12) Hyperparameter Optimization

[0119] Given N state observations ,..., And the corresponding target output ,..., , then using the probability distribution Represents the likelihood function based on the training data:

[0120] (2);

[0121] in Output training data matrix for the target, is the state data training matrix, is the hyperparameter vector, is the covariance matrix of the training data. Therefore, the optimal hyperparameters can be optimized by maximizing the likelihood function:

[0122] (3);

[0123] It can be seen that the optimization process requires calculation Partial derivatives with respect to each hyperparameter:

[0124] 13) Prediction

[0125] Finding the optimal hyperparameters After that, we can use the relevant training data , i=1,...,N for any state to be tested Make a prediction, and its output is expressed as Therefore, we can get Unbiased estimate of :

[0126] (4);

[0127] (5);

[0128] in, is the covariance vector between the test sample and the training sample, is the covariance between the sample to be tested and itself.

[0129] 2) Fault feature extraction

[0130] Details of the fault feature extraction method based on instantaneous Gaussian processes, including the selection of relevant samples using similarity estimation, local model estimation using Gaussian processes, and the generation of residual vectors as fault features based on predicted outputs and measurement results.

[0131] 21) Similar sample selection

[0132] In the instant Gaussian process method, it is necessary to select a part of the data that is most relevant to the sample to be tested to establish a local model, so a similarity evaluation criterion is needed as a standard for selecting data. and The commonly used distance metrics and similarity evaluations are as follows:

[0133] Distance metrics:

[0134] Euclidean distance is a commonly used distance metric that defines the spatial distance between two samples.

[0135] Manhattan distance, also known as block distance;

[0136] Minkowski distance, a generalization of Euclidean distance and Manhattan distance;

[0137] Similarity evaluation:

[0138] Cosine similarity considers the angle between the vectors of two samples; it is used to measure the angle between two vectors. The smaller the angle, the greater the cosine similarity.

[0139] Pearson similarity reflects linear similarity.

[0140] The similarity between the current sample to be tested and the dataset is evaluated using a combined similarity criterion consisting of the exponential of the Euclidean distance between two vectors and the cosine similarity to improve the estimation ability. With historical data samples The similarity between them can be written as:

[0141] (6);

[0142] in, is the weight factor, express and The angle between here , , Represents the current sample and The similarity of The larger the and The higher the similarity between them. In addition, Must be greater than 0, that is, .if , it is considered that the two vectors that make up this angle are not similar, and the corresponding database samples are not considered when establishing the local model. .

[0143] After similarity evaluation, a data subset can be constructed using related data , Corresponding to greater similarity ,in The number of samples used to build the instant local model.

[0144] 22) Local model prediction based on Gaussian process

[0145] Consider a sample state to be predicted as x, whose output is unknown and represented by y. To simplify the calculation, assume that the elements of each dimension in y are are independent of each other. The prediction problem of can be decomposed into the self-problem of predicting each of its elements: According to the Gaussian process prediction method, after Gaussian process modeling and hyperparameter optimization, we can get Prediction: According to formula (4), we can get It is an unbiased estimate, and the mean square error of this estimate can be calculated by formula (5) . Then we can get the predicted value of y. The implementation of the above algorithm requires the inversion of the covariance matrix K, and its computational complexity is , the storage complexity is , when the amount of training data is large, the computational cost may be very high. This problem can be solved by the natural advantages of instant learning: , that is, training data The number of is much smaller than the amount of data in the dataset N, and the dimension of the K matrix will be greatly reduced, so the amount of calculation for its inversion will be greatly reduced.

[0146] 23) Residual calculation

[0147] To generate residuals as fault signatures for fault detection and diagnosis, the instantaneous Gaussian process simulates the behavior of real nonlinear and dynamic systems in healthy conditions. The residual is the difference between the estimated output and the actual observed value. It eliminates the dynamics and nonlinearity of the process and extracts the essential information of the fault. It is calculated as follows:

[0148] (7);

[0149] Among them, y and They are the measured output and predicted output in the current state respectively.

[0150] 3) Fault classification based on extreme learning machine

[0151] like Figure 3 , when the input of a single hidden layer feedforward neural network is an m-dimensional vector r, its output is:

[0152] (8);

[0153] Where L is the number of hidden neurons; is the input layer weight vector connecting the input vector and the i-th hidden layer neuron, m is the dimension of the input vector, is the weight vector connecting the output vector and the i-th hidden layer neuron, and o is the number of output layer nodes; is the hidden layer activation function, represents the bias of the i-th hidden layer neuron, is the output of the i-th hidden layer neuron.

[0154] Then, given N samples , ,in , , we can construct N output results similar to formula (8):

[0155] (9);

[0156] in,

[0157] , , , , , .

[0158] H is the hidden layer output matrix, where The first The output of the jth hidden layer neuron can be obtained by assigning random hidden layer neuron parameters to Then the calculation is performed. The minimum norm and least squares solution of formula (9) are:

[0159] (10);

[0160] in is the generalized inverse matrix of H.

[0161] For classification problems, the extreme learning machine can be set to a multi-output structure with o output nodes, where O is the number of categories in the classification problem. When the category label is k, the expected output vector is , the kth element is 1 and the rest are 0. When dealing with multi-classification problems, the index number of the maximum value of the output node is used as the predicted category of the test input. Therefore, when the input is When , the estimated fault state is:

[0162] (11);

[0163] in , is the output of the jth node.

[0164] In order to train the extreme learning machine network, a dataset failure dataset is required ,in It is necessary to include status-output data under normal and various fault conditions, is the label data corresponding to the fault state. Then, the estimated residual calculated by the instantaneous Gaussian process is and the corresponding fault status labels , construct the training data set of the extreme learning machine After determining the network weight parameters and activation function, the training process is completed and the ELM fault classifier can be obtained.

[0165] To more clearly illustrate how to use the ELM fault classifier to perform permanent magnet synchronous motor drive fault diagnosis, refer to the following case:

[0166] 1. Building an Instant Gaussian Process Model

[0167] 1. Data preparation

[0168] Collect a large amount of historical data from the permanent magnet synchronous motor drive during normal operation, including operating environment data (ambient temperature, electromagnetic interference level, power supply stability), command completion data (average command response time, dynamic response time, steady-state achievement time), and operating status data (motor winding impedance, circuit harmonic content, DC link voltage, rotor offset). Assume that we collected data every 10 minutes for the past month, resulting in a total of 4,320 data samples.

[0169] This data is preprocessed to ensure accuracy and completeness. For example, outlier detection and correction are performed on ambient temperature data to remove obviously erroneous measurements; and time series alignment is performed on instruction completion data to ensure that the execution time data of different instructions is on the same time scale.

[0170] 2. Gaussian process prior model setting

[0171] Assume that the operating status of the motor driver can be described by a function Indicates that x is the input data vector (including the various operating data parameters mentioned above). In the Gaussian process prior model, for any point x, is assumed to be a random variable.

[0172] Determine the covariance function, for example, select the above formula (1). For this embodiment, is 1.5.

[0173] 3. Hyperparameter Optimization

[0174] Given the above 4320 state observations and the corresponding target outputs (e.g., a label indicating whether the motor is operating normally in this state, 0 for normal and 1 for fault), a target output training data matrix and a state data training matrix are constructed.

[0175] Hyperparameters are optimized by maximizing the likelihood function based on the training data using a probability distribution. Gradient descent or other optimization algorithms are used to solve the problem. During the optimization process, the partial derivative of the likelihood function with respect to each hyperparameter is calculated. The hyperparameter value is adjusted based on the direction and magnitude of the partial derivative. After multiple iterations, the optimal hyperparameter value is ultimately obtained.

[0176] 2. Fault Feature Extraction

[0177] 1. Similar sample selection

[0178] When the current operating status of the motor drive needs to be diagnosed, the current operating data is obtained as the test sample. The combined similarity between the current test sample and the historical data sample is calculated. For example, a combined similarity criterion consisting of the exponential of the Euclidean distance and the cosine similarity is used, as shown in Formula (6).

[0179] 2. Local model prediction based on Gaussian process

[0180] Consider the current state of the sample to be tested, whose output is unknown. Decompose the prediction problem into sub-problems for predicting its individual elements. Using the Gaussian process prediction method, using the previously established Gaussian process model (with optimized hyperparameters) and the selected relevant samples, calculate the covariance vector between the test sample and the training samples, as well as the covariance between the test sample and itself.

[0181] According to formula (4), we can get It is an unbiased estimate, and the mean square error of this estimate can be calculated by formula (5) , and then we can get the predicted value of y.

[0182] 3. Residual calculation

[0183] Measure the actual output value of the current motor driver, such as the actual measured motor winding impedance and the actual response time after command execution. Calculate the residual, formula (7). This residual contains information about the difference between the current system operating state and the state predicted by the health model, which may indicate a potential fault. For example, if the residual of the calculated motor winding impedance exceeds the normal fluctuation range, it may indicate a problem with the motor winding, such as insulation aging or a local short circuit.

[0184] 3. Fault Classification

[0185] Construct an extreme learning machine (ELM) training dataset, using the residual vectors calculated above as input features, along with the corresponding fault state labels (determined through actual fault detection or expert judgment). For example, if a specific residual pattern consistently accompanies a motor winding fault in past fault cases, the fault label corresponding to that residual pattern is a motor winding fault.

[0186] Determine the network structure of ELM, including selecting the appropriate number of hidden layer neurons, activation function, etc. For example, select the number of hidden layer neurons as 50 and the activation function as sigmoid function.

[0187] Randomly initialize the input layer weight vector and hidden layer neuron bias, calculate the hidden layer output matrix, and then calculate the output layer weight vector according to formula (10) to complete the ELM training process.

[0188] 2. Fault type determination

[0189] When new real-time operating data is acquired and the residual is calculated, it is fed into the trained ELM to generate the output. For example, the output of the ELM might be a vector, where each element represents the probability or likelihood of a certain motor drive failure.

[0190] The fault type is determined based on the output results. The index of the maximum output node value is typically selected as the predicted category for the test input. If the third element in the output vector has the largest value and the fault type corresponding to that element is a rotor offset fault, then the motor drive is likely experiencing a rotor offset fault, thus accurately classifying the permanent magnet synchronous motor drive fault type.

[0191] In addition, a database including multiple fault types can also be established, in which fault feature data corresponding to various fault types and data on normal operation of the drive are stored. The real-time operation data is input into the database, and similarity analysis (including but not limited to Euclidean distance and Manhattan distance) is performed between the real-time operation data and each fault feature data. The fault feature data closest to the real-time operation data (or the data on normal operation of the drive) can be found, that is, the minimum similarity value is determined, so that the fault type can be determined and fault classification can be achieved.

[0192] This embodiment can be implemented based on the following hardware:

[0193] The electronic device includes: a processor and a memory, wherein computer program instructions are stored in the memory, and when the computer program instructions are executed by the processor, the processor executes the above permanent magnet synchronous motor drive fault diagnosis method based on the fault classifier.

[0194] A computer-readable storage medium is used to store a program, and when the program is executed by a processor, the permanent magnet synchronous motor drive fault diagnosis method based on the fault classifier is implemented.

Claims

1. A permanent magnet synchronous motor drive fault diagnosis method based on a fault classifier, characterized in that: The following steps are involved: During a diagnostic cycle, the operating environment data of the permanent magnet synchronous motor drive's environment is obtained. Based on the operating environment data, it is determined whether the permanent magnet synchronous motor drive's operating environment is normal. The operating environment data includes ambient temperature, electromagnetic interference level, and power supply stability: If the operating environment is abnormal, the real-time operating data of the permanent magnet synchronous motor drive is obtained and input into the fault classifier pre-stored in the database. The real-time operating data includes the motor winding impedance, circuit harmonic content, DC link voltage and rotor offset. If the operating environment is normal, the instruction completion status of the permanent magnet synchronous motor driver is evaluated to determine whether the instruction completion status of the permanent magnet synchronous motor driver is normal, including the following steps: Obtain command completion data for permanent magnet synchronous motor drivers, including average command response time, dynamic response time, and steady-state achievement time. Obtain instruction completion parameter data stored in the database, including instruction parameter average response time, parameter dynamic response time, and parameter steady-state achievement time; Obtain the allowable deviation data of the instruction completion status, including the allowable deviation value of the dynamic response time and the allowable deviation value of the steady-state achievement time; Obtaining an instruction completion status evaluation value based on instruction completion status data, instruction completion status parameter data, and instruction completion status allowable deviation data; Determine whether the instruction completion evaluation value is greater than the instruction completion evaluation threshold stored in the database: If the instruction completion evaluation value is greater than the instruction completion evaluation threshold stored in the database, the instruction completion status is abnormal; If the instruction completion evaluation value is not greater than the instruction completion evaluation threshold stored in the database, the instruction completion is normal; If the instruction completion is abnormal, the real-time operation data of the permanent magnet synchronous motor driver is obtained and the real-time operation data is input into a fault classifier pre-stored in the database; If the command is completed normally, the real-time operation data of the permanent magnet synchronous motor driver is obtained, and based on the real-time operation data, it is determined whether the operation status of the permanent magnet synchronous motor driver is normal: If the operating status is normal, enter the next diagnostic cycle; If the operating state is abnormal, real-time operating data of the permanent magnet synchronous motor driver is obtained and the real-time operating data is input into a fault classifier pre-stored in the database; The fault classifier pre-stored in the database diagnoses the real-time operation data to determine the fault type of the permanent magnet synchronous motor drive.

2. The permanent magnet synchronous motor drive fault diagnosis method based on the fault classifier according to claim 1 is characterized in that: Judging whether the operating environment of the permanent magnet synchronous motor drive is normal based on the operating environment data includes the following steps: Obtain operating environment parameter data stored in the database, including ambient temperature, electromagnetic interference level, and power supply stability; The operating environment data is integrated and analyzed with the operating environment parameter data to obtain the operating environment evaluation index; Determine whether the operating environment assessment value is greater than the operating environment assessment threshold stored in the database: If the operating environment evaluation value is greater than the operating environment evaluation threshold stored in the database, the operating environment is abnormal; If the operating environment evaluation value is not greater than the operating environment evaluation threshold stored in the database, the operating environment is normal.

3. The permanent magnet synchronous motor drive fault diagnosis method based on the fault classifier according to claim 2 is characterized in that: The method for obtaining the operating environment evaluation value is as follows: ； Where, Yp is the operating environment assessment value, WsH is the ambient temperature, Ds is the electromagnetic interference level, Ws is the power supply stability, WcH is the ambient parameter temperature, Dc is the parameter electromagnetic interference level, and Wc is the parameter power supply stability.

4. The permanent magnet synchronous motor drive fault diagnosis method based on the fault classifier according to claim 1 is characterized in that: Obtaining instruction completion tolerance data includes the following steps: Based on the device information of the permanent magnet synchronous motor drive, a matching data set is obtained from the database, where the matching data set includes multiple deviation value matching data, and the deviation value matching data includes an electromagnetic interference matching value, a power supply stability matching value, and a daily average temperature of the drive; Obtain the data to be matched for the permanent magnet synchronous motor drive, including electromagnetic interference level, power supply stability, and actual drive temperature; Compare the data to be matched with each deviation value matching data one by one, and determine the deviation value matching data closest to the data to be matched; The instruction completion status allowable deviation data corresponding to the deviation value matching data stored in the database is obtained.

5. The permanent magnet synchronous motor drive fault diagnosis method based on the fault classifier according to claim 4 is characterized in that: Comparing the data to be matched with each deviation value matching data one by one to determine the deviation value matching data closest to the data to be matched, including the following steps: Obtaining matching values ​​after comparing the data to be matched with the matching data of each deviation value; Determine the minimum matching value; The deviation value matching data corresponding to the minimum matching value is output as the deviation value matching data closest to the data to be matched.

6. The permanent magnet synchronous motor drive fault diagnosis method based on the fault classifier according to claim 5 is characterized in that: The method for obtaining the matching value is as follows: ； Where PP is the matching value, Ds is the electromagnetic interference level, Ws is the power supply stability, Qsw is the actual temperature of the driver, Dp is the electromagnetic interference matching value, Wp is the power supply stability matching value, Qcw is the average daily temperature of the driver, e is a natural constant, and ln is a logarithmic function, which represents the logarithm with base e.

7. The permanent magnet synchronous motor drive fault diagnosis method based on the fault classifier according to claim 1 is characterized in that: Judging whether the operating status of the permanent magnet synchronous motor drive is normal based on real-time operating data includes the following steps: Obtain the operating status parameter data of the permanent magnet synchronous motor drive stored in the database, including the motor winding parameter impedance, parameter circuit harmonic content, DC link parameter voltage and rotor parameter offset; Obtaining the allowable deviation data of the operating status, including the allowable deviation value of the motor winding parameter impedance and the allowable deviation value of the DC link parameter voltage; The operating status of the permanent magnet synchronous motor drive is evaluated based on real-time operating data, operating status parameter data and operating status allowable deviation data to determine whether the operating status is normal.

8. The permanent magnet synchronous motor driver fault diagnosis method based on the fault classifier according to claim 7 is characterized in that: The operating status of the permanent magnet synchronous motor drive is evaluated based on real-time operating data, operating status parameter data, and operating status allowable deviation data to determine whether the operating status is normal, including the following steps: Obtaining an operating status evaluation index based on real-time operating data, operating status parameter data, and operating status allowable deviation data; Determine whether the running status evaluation index is greater than the running status evaluation threshold stored in the database: If the running status evaluation index is greater than the running status evaluation threshold stored in the database, the running status is abnormal; If the running status evaluation index is not greater than the running status evaluation threshold stored in the database, the running status is normal.

9. The permanent magnet synchronous motor driver fault diagnosis method based on fault classifier according to claim 7, characterized in that: Obtaining the operating status allowable deviation data includes the following steps: Obtain operating status matching data for permanent magnet synchronous motor drives, including the average daily continuous use time of the drive, electromagnetic interference level, and power supply stability; Compare the operating status matching data with each state deviation matching data stored in the database one by one to obtain the comparison coefficient. The state deviation matching data includes the matching parameters of the average continuous use time of the drive per day, the electromagnetic interference level matching parameters, and the power supply stability matching parameters. Determine the minimum comparison coefficient and extract the operating state allowable deviation data corresponding to the minimum comparison coefficient from the database.

Images