A method for fault diagnosis of permanent magnet synchronous motor

Abstract

The present invention discloses a permanent magnet synchronous motor fault diagnosis method, comprising the following steps: converting currently collected three-phase current and three-phase voltage into current and voltage on the d-axis and q-axis; calculating theoretical voltage values ​​and theoretical current values ​​on the d-axis and q-axis respectively based on the current and voltage on the d-axis and q-axis; obtaining a voltage prediction value at the current moment based on the theoretical voltage value and operating parameters at the current moment, and obtaining a current prediction value at the current moment based on the theoretical current value and operating parameters at the current moment; performing anomaly detection based on the difference between the voltage prediction value and the current prediction value and the corresponding collected values, and determining the fault type of the motor when an anomaly is detected in the motor. The difference index fully considers the difference between the current and voltage on the d-axis and the q-axis, and can more comprehensively reflect the degree of deviation between the motor operating state and the model prediction, thereby improving the accuracy of fault diagnosis.

Description

Technical Field

[0001] The present invention belongs to the technical field of motor control, and more specifically, to a permanent magnet synchronous motor fault diagnosis method. Background Art

[0002] Permanent magnet synchronous motors (PMSMs) are highly favored in the industrial sector due to their superior performance, stability, and compact design. However, PMSMs can experience a variety of faults during operation, such as rotor eccentricity, stator winding short circuits, and permanent magnet demagnetization. These problems not only disrupt the normal operation of the motor but can also pose serious safety risks.

[0003] Traditional fault diagnosis techniques often rely on experience and data from specific sensors. These techniques have the following drawbacks:

[0004] (1) High dependence: Traditional methods are highly dependent on the detection signals of sensors. When the sensor detection shows a mutation or abnormality, the reliability of the entire diagnostic system will be greatly reduced;

[0005] (2) Insufficient accuracy: Experience-based diagnostic methods are difficult to fully cover all possible failure modes, resulting in a high misdiagnosis rate;

[0006] (3) Poor adaptability: Existing technologies lack sufficient adaptability to PMSMs of different models and operating conditions, and diagnostic strategies need to be designed separately for each situation. Summary of the Invention

[0007] The present invention provides a permanent magnet synchronous motor fault diagnosis method, aiming to improve at least one of the above problems.

[0008] The present invention is implemented as follows: a permanent magnet synchronous motor fault diagnosis method, the method comprising the following steps:

[0009] (1) Convert the currently collected three-phase current and three-phase voltage into the current and voltage on the d-axis and q-axis;

[0010] (2) Calculate the theoretical voltage values ​​on the d-axis and q-axis based on the current and voltage on the d-axis and q-axis respectively and Theoretical current value and

[0011] (3) Based on the theoretical voltage value at the current moment and and operating parameters to obtain the current voltage forecast value and Based on the theoretical current value at the current moment and and operating parameters to obtain the current forecast value at the current moment and

[0012] (4) Anomaly detection is performed based on the difference between the voltage prediction value and the current prediction value and the corresponding collected value. When an abnormality is detected in the motor, the fault type of the motor is determined.

[0013] Furthermore, the current theoretical current value The current operating data includes three-phase voltage, three-phase current and motor temperature T, which form an input vector and are input into the trained first LSTM network. The first LSTM network outputs the current prediction value at the current moment. and

[0014] Furthermore, the current theoretical voltage value and The current operating data includes three-phase voltage, three-phase current and motor temperature T, which form an input vector and are input into the trained second LSTM network. The second LSTM network outputs the voltage prediction value at the current moment. and

[0015] Furthermore, the threshold update formula of the first LSTM network or the second LSTM network is as follows:

[0016] θ b =βθ n +(1-β)α[D n -θ n ]

[0017] Among them, θ n The threshold formed by the last threshold update is also the threshold before this update. n is the difference index after updating based on the running data collected at the current time interval, θ b This is the threshold formed after this update, α is the learning rate, and β is the forgetting factor.

[0018] Furthermore, the initial value determination process of the threshold is as follows:

[0019] Based on the difference indicator sequence {D1, D2, ..., D m}Construct the normal distribution probability density function f(D) of the difference index D: According to the maximum likelihood estimation principle, construct the likelihood function L(μ,σ), and determine the estimated values ​​of μ and σ based on the likelihood function L(μ,σ). The initial value of the threshold θ0=μ+3σ, where μ and σ are the parameters of the normal distribution.

[0020] Furthermore, anomaly detection is performed on the collected operating data. The outlier detection process is as follows:

[0021] Determine the i-th running data x based on historical data i The mean μ i and standard deviation σ i , for the currently collected running data x i , judge |x i -μ i |>3σ i Is it true? If so, the currently collected running data x i For outliers, replace them with the average of the adjacent normal values.

[0022] Furthermore, the difference index D corresponding to the current running data is calculated based on the following formula:

[0023]

[0024] in, It represents the d-axis current and q-axis current obtained by converting the three-phase current collected at the kth moment. It represents the d-axis voltage and q-axis voltage obtained by converting the three-phase voltage collected at the kth moment. They represent the predicted values ​​of d-axis current, q-axis current, d-axis voltage, and q-axis voltage output by the anomaly detection model at the kth moment, respectively, and n represents the total number of the nearest historical sampling points.

[0025] Furthermore, the abnormality determination process of the motor is as follows:

[0026] When the current difference index D>θ1, and the number of times the difference index D corresponding to the past 10 sampling points is greater than the primary threshold θ1 exceeds 60%, it is determined that the motor is abnormal, where θ1 is set to 0.7 times the current threshold;

[0027] When the current difference index D>θ2, and the number of times the difference index D corresponding to the past 20 sampling points is greater than the intermediate threshold θ2 exceeds 70%, and the average value of the difference index shows an increasing trend, θ2 is set to 1.1 times the current threshold;

[0028] When the current difference index D>θ3, and in the past 30 sampling points, the number of times the difference index D is greater than the advanced threshold θ3 exceeds 80%, and the average value of the difference index continues to increase and the increase rate exceeds a set growth threshold, where θ3 is set to 1.3 times the current threshold.

[0029] Furthermore, after being determined to be abnormal, the mean, variance, and spectral characteristics of the current current and voltage of the motor are input into the fault prediction models of various types of faults, and the current fault type of the motor is determined based on the prediction results output by each fault prediction model.

[0030] Furthermore, a fault prediction model is constructed for each type of fault. The fault prediction model is constructed using a convolutional neural network, and all fault prediction models are placed in a fault prediction model library.

[0031] The fault diagnosis method for a permanent magnet synchronous motor provided by the present invention has the following beneficial technical effects:

[0032] (1) Improved diagnostic accuracy: The current and voltage prediction model provided by the present invention comprehensively considers the physical characteristics of the motor and the nonlinear relationship in the actual operating data. Compared with traditional methods, it is more accurate in judging motor abnormalities. A detailed difference index calculation method is adopted, which fully considers the differences between current and voltage on the d-axis and q-axis, and can more comprehensively reflect the degree of deviation between the motor operating status and the model prediction, thereby improving the detection accuracy of motor abnormalities.

[0033] (2) Reduce false alarm rates: The combination of motor physical models and machine learning models (such as long short-term memory networks (LSTMs)) avoids misjudgments caused by the limitations of a single model. The physical model is based on the basic principles of the motor and has basic constraints on normal operating conditions. The machine learning model, by learning complex relationships in large amounts of data, can supplement situations that are difficult for the physical model to handle. The two work together to effectively reduce false alarms caused by a single factor.

[0034] (3) Improved response speed: Real-time monitoring of motor operating parameters, with a short data collection interval (data is collected every 5 milliseconds), enables timely acquisition of the latest motor operating status. Once the difference between the measured data and the model prediction value exceeds the abnormality judgment standard, fault detection is immediately initiated, enabling rapid diagnosis of the fault in a short period of time. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flow chart of a permanent magnet synchronous motor fault diagnosis method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The specific implementation methods of the present invention will be further explained in detail below by describing the embodiments with reference to the accompanying drawings, so as to help those skilled in the art to have a more complete, accurate and in-depth understanding of the inventive concept and technical solution of the present invention.

[0037] The present invention provides a permanent magnet synchronous motor fault diagnosis method based on model difference analysis. First, a physical model of the PMSM is established. Based on the current physical model, the theoretical values ​​corresponding to the current operating parameters are calculated. Based on the monitoring of the actual operating parameters and the corresponding theoretical values, the current and voltage of the motor are predicted. Then, the difference index between the predicted value and the measured value is calculated. The motor abnormality is detected based on the difference index. After the current abnormality of the permanent magnet synchronous motor is detected, it is matched with the fault detection models of various faults in the fault model library to determine the fault type of the motor, such as Figure 1 shown.

[0038] (1) Physical model: Based on the basic physical equations of the motor, a physical model of the motor during normal operation is constructed. The calculation formula of the d-axis (direct axis) voltage is as follows:

[0039]

[0040] The calculation model of the q-axis (quadrature-axis) voltage is as follows:

[0041]

[0042] Among them, V d 、V q are the voltages on the d-axis and q-axis respectively, R s is the stator resistance, L d , L q are the d-axis and q-axis inductances, ω e is the angular velocity of the motor, I d , I q are the currents of the d-axis and q-axis respectively, λ r is the magnetic flux generated by the permanent magnet.

[0043] In order to determine the parameters in the physical model (R s , L d , L q ,λ r First, the basic data of the motor, such as voltage, current and speed, under different working conditions, are measured through no-load and short-circuit tests. Then, based on these experimental data, the motor equivalent circuit theory and electromagnetic field theory are used to calculate the parameters. For example, the voltage and speed data measured by the no-load test are combined with the V q =ω e λ r (No-load I q ≈0) to calculate the permanent magnet flux; the stator resistance R is calculated by combining the short-circuit current and voltage data measured by the short-circuit experiment with the short-circuit equivalent circuit equation. s and inductance (L d , L q ) and other parameters.

[0044] The detailed no-load test steps are as follows: Connect the motor to the driver and operate it in a no-load state. Gradually increase the motor speed to the rated speed and allow it to run steadily for a period of time. During this process, use high-precision voltage and current sensors to measure the motor's phase voltage and phase current, while a speed sensor measures the motor speed. Record a set of data at regular intervals (10 seconds), collecting a total of N sets of data (N ≥ 100). For the short-circuit test, short-circuit one of the motor's phase windings (for example, short-circuit the U phase winding). While the motor is stationary, apply a specific DC voltage (this voltage should be lower than the motor's rated voltage to prevent damage from excessive current) and measure the short-circuit current and voltage. Repeat the short-circuit test multiple times (3–5 times) and take the average value as the final short-circuit test data for calculating the stator resistance and inductance.

[0045] (2) Data Acquisition: The three-phase current, three-phase voltage, and motor temperature of the permanent magnet synchronous motor are collected at fixed time intervals (5ms) during operation. High-precision sensors (current sensor accuracy reaches ±0.2%, voltage sensor accuracy reaches ±0.1%, and temperature sensor accuracy reaches ±0.5°C) are used to ensure data accuracy. The collected data is transmitted to a computer for subsequent processing via a high-speed data acquisition card. The sampling frequency of the data acquisition card is set to 20kHz to meet the requirements of high-frequency signal acquisition.

[0046] The hardware architecture of a data acquisition system consists of a sensor module, signal conditioning circuitry, a data acquisition card, and a computer. The sensor module converts the motor's operating parameters (current, voltage, temperature, etc.) into electrical signals. The signal conditioning circuitry amplifies, filters, and performs analog-to-digital conversion on the sensor's output signals to meet the input requirements of the data acquisition card. The data acquisition card converts the analog signals into digital signals and transmits them via a high-speed bus to the computer's memory for storage and processing.

[0047] (3) Data preprocessing: A Kalman filter is used to remove noise from the collected data. The Kalman filter's state equation and observation equation are determined based on the motor's dynamic model and measurement model. A recursive algorithm is used to estimate and correct data in real time, effectively filtering out measurement noise and system noise. Current and voltage data are also normalized to a value between 0 and 1 to facilitate subsequent model calculations.

[0048] (4) Current and voltage prediction: In order to reduce the impact of sudden changes in the collected values ​​of operating parameters, a neural network - long short-term memory network (LSTM) is used to predict the current current and voltage of the motor. The LSTM network structure consists of an input layer, a hidden layer (containing 50 LSTM units) and an output layer. The preprocessed normal operation data is divided into a training set (80%), a validation set (10%) and a test set (10%). The LSTM network is trained using the training set. The training algorithm uses the adaptive moment estimation (Adam) optimization algorithm. The learning rate is initially set to 0.001, β1 = 0.9, β2 = 0.999, and the number of training iterations is 2000. Through training, the LSTM network is able to capture the temporal dependencies and nonlinear characteristics in the motor operation data.

[0049] The training process of the LSTM network is as follows: the training set data is input into the LSTM network in time series order. The input data of each time step includes three-phase current, three-phase voltage and motor temperature. For the input data, necessary format conversion and dimension adjustment are performed to make it meet the input requirements of the LSTM network. At each time step, the LSTM unit is based on the input data and the hidden state h at the previous moment. t-1 and cell state c t-1 , calculate the hidden state h at the current moment t and cell state c t , and obtains the predicted value through the output layer. The loss function between the predicted value and the actual value is calculated, and the gradient is calculated through backpropagation using the Adam optimization algorithm to update the weights and bias parameters of the LSTM network. This process is repeated until the set number of training iterations is reached or the loss function converges below a certain threshold.

[0050] The above physical model is combined with the trained LSTM network model. The physical model provides constraints on the basic operating principles of the motor, and the LSTM network model supplements the nonlinear and dynamic characteristics that are difficult to accurately describe with the physical model.

[0051] For current prediction, the d-axis voltage and q-axis voltage at the current moment are calculated based on the three-phase voltage collected at the current moment, and the d-axis voltage and q-axis voltage are input into the physical model, which calculates the theoretical current value based on the current moment. and The current theoretical current value The collected current operating data includes three-phase voltage, three-phase current and motor temperature, which constitute the input vector Among them, V a 、V b 、V c is the three-phase voltage of the motor, I a , I b , I cis the three-phase voltage of the motor, T is the temperature of the motor, and is input into the trained first LSTM network. The first LSTM network outputs the current prediction value at the current moment based on the input vector and the previously learned time series dependency relationship for the current and

[0052] For voltage prediction, the d-axis current and q-axis current at the current moment are calculated based on the three-phase current collected at the current moment, and the d-axis current and q-axis current are input into the physical model, which calculates the theoretical voltage value at the current moment. and The current theoretical voltage value The input vector is composed of the currently collected operating data including three-phase voltage, three-phase current and motor temperature. The second LSTM network outputs the current voltage prediction value based on the input vector and the previously learned temporal dependency relationship for voltage. and

[0053] The prediction ability of the hybrid model under normal operating conditions is evaluated by leave-one-out cross-validation. For each sample, it is used as a test sample, and the remaining samples are used as training samples for model training and prediction. The mean absolute error (MAE) between the predicted value and the actual value is calculated using the formula:

[0054]

[0055] Among them, m is the number of samples, y i is the actual value of the i-th sample, is the predicted value of the i-th sample. If the MAE is less than the set threshold, the model's predictive ability is considered to meet the requirements; otherwise, adjust the parameters of the LSTM network model (such as increasing the number of hidden layer units or adjusting the learning rate), retrain and verify until the requirements are met.

[0056] During the leave-one-out cross-validation process, detailed records are kept of each training and prediction result, including the MAE value and the distribution of deviations between the predicted and actual values. Analysis of these results assesses the model's generalization and stability across different samples. If certain samples result in large model prediction errors, further analysis may reveal factors such as data anomalies or unusual motor operating conditions. In these cases, further data processing or adjustments to the model structure may be considered to improve model robustness.

[0057] (5) Difference analysis: Input the measured data (current, voltage and other data after preprocessing) into the LSTM network and calculate the corresponding predicted value. and And the voltage prediction value and Calculate the difference between the predicted value and the measured value and define the difference index D:

[0058]

[0059] in, It represents the d-axis current and q-axis current obtained by converting the three-phase current collected at the kth moment. It represents the d-axis voltage and q-axis voltage obtained by converting the three-phase voltage collected at the kth moment. represents the predicted values ​​of the d-axis current, q-axis current, d-axis voltage, and q-axis voltage output by the anomaly detection model at the kth moment, respectively. n represents the total number of historical sampling points. To prevent individual abnormal data points from significantly influencing the difference index, outlier detection and processing are performed on the measured and predicted values ​​before calculating the difference. The 3-standard deviation method is used to identify outliers and replaces them with the average of the adjacent normal data points.

[0060] The collected operating data is subjected to abnormality detection. The abnormal value detection process is as follows: First, the motor i-th operating data x is obtained. i The mean μ i and standard deviation σ i , for the currently collected running data x i , judge |x i -μ i |>3σ i Is it true? If so, it is considered that the currently collected running data x i For abnormal values, replace the abnormal values ​​with the average value of the adjacent normal values. When calculating the difference index D, the processed measured values ​​and predicted values ​​are used for calculation to improve the reliability of the difference index. i It is three-phase voltage, three-phase current and motor temperature.

[0061] (6) Threshold update: Based on a large amount of historical data (covering data under normal operation and various fault conditions of the motor, with a data volume of no less than 5,000 groups) and experimental results, an empirical threshold θ0 is preliminarily set.

[0062] The specific operations are as follows;

[0063] First, statistical analysis is performed on the difference index D in the historical data, and its mean μ and standard deviation σ are calculated. Assuming that the difference index D follows the normal distribution N(μ, σ 2To ensure the rationality of the normal distribution assumption, the Shapiro-Wilk normality test method was used to test the data. If the test results showed that the data did not obey the normal distribution, the data were logarithmically transformed or square-rooted to make them approximately obey the normal distribution before subsequent calculations.

[0064] Then, the parameters μ and σ of the normal distribution are estimated by the maximum likelihood estimation method. m} (m is the number of data points), construct the probability density function f(D) of the normal distribution:

[0065]

[0066] According to the maximum likelihood estimation principle, the likelihood function L(μ,σ) is constructed:

[0067]

[0068] Taking the logarithm of the likelihood function yields:

[0069]

[0070] Taking partial derivatives of μ and σ and setting them to 0, we get the following equations:

[0071]

[0072] Solve this system of equations to get the estimated values ​​of μ and σ. Take the initial value of the threshold θ0 = μ + 3σ.

[0073] In this way, under normal operating conditions, the probability of the difference indicator exceeding the threshold is approximately 0.3%, effectively reducing the false alarm rate during normal operation. At the same time, to further improve the accuracy of the initial threshold setting, a cross-validation method can be used to divide the historical data into a training set and a validation set. The initial threshold is calculated on the training set, and then its effectiveness is verified on the validation set. The threshold is fine-tuned based on the verification results. The specific formula for using adaptive threshold adjustment is as follows:

[0074] θ b =θ n +α[D n -θ n ];

[0075] Among them, θ n The threshold formed by the last threshold update is also the threshold before this update. n is the difference index updated based on the currently collected operating data, θ bThis is the threshold formed after this update, α is the learning rate (the value range is between 0.05-0.2, initially set to 0.1), which controls the speed of threshold update.

[0076] After a certain time interval (30 seconds) or a certain amount of new data (500 new data points) is collected, the difference index is recalculated and the threshold is updated according to the above formula. During the threshold update process, to prevent the threshold from being adjusted too frequently or fluctuating too much, a threshold adjustment step limit is set (each adjustment range does not exceed 10% of the previous threshold). At the same time, a forgetting factor β (ranging from 0.8 to 0.99) is introduced to weight the impact of historical data so that the threshold can better reflect the current system operating status. The threshold update formula is as follows:

[0077] θ b =βθ n +(1-β)α[D n -θ n ];

[0078] To ensure the effectiveness of dynamic threshold adjustment, in actual applications, the fault detection performance after threshold adjustment can be monitored in real time, such as changes in false alarm and missed alarm rates. If a significant increase in false alarm or missed alarm rates is observed, threshold adjustment can be paused and the cause analyzed. This may be due to a significant change in the motor's operating conditions (such as a sudden load change or ambient temperature change). In this case, the threshold can be manually adjusted or the learning rate α and forgetting factor β can be adjusted based on the specific situation before continuing with dynamic threshold adjustment.

[0079] (7) Abnormality judgment: Primary threshold θ1 (value is 0.7θ b ), when D > θ1, the motor is considered to have an abnormality. To avoid misjudgments due to fluctuations in individual data points, the motor abnormality is determined not only by the current difference index D being greater than the primary threshold θ1, but also by the number of times that the difference index D corresponding to the past 10 sampling points has exceeded the primary threshold θ1 for more than 60%.

[0080] Intermediate threshold θ2 (valued at 1.1θ b ), when D>θ2, the suspicion of fault is further increased. When judging whether there is an abnormality in the motor, the changes in the difference index in the past period of time are also considered. It is required that the number of times the difference index D corresponding to the past 20 sampling points is greater than the intermediate threshold θ2 exceeds 70%. The 20 sampling points are grouped, and the average value of the difference index in each group is required to show an upward trend.

[0081] Advanced threshold θ3 (valued at 1.3θ bWhen D > θ3, the motor is essentially faulty. To avoid misjudgments due to fluctuations in individual data points, the motor anomaly is determined to exist if, over the past 30 sampling points, the difference index D exceeds the advanced threshold θ3 more than 80% of the time, and the average value of the difference index continues to rise and exceeds a set growth threshold. The 30 sampling points are grouped, and the average value of the difference index in each group must differ by at least 0.1 from the average value of the previous group.

[0082] The duration determination for each threshold level is based on an understanding of the motor fault development process. Motor faults typically do not occur instantaneously but rather develop over a period of time. By setting duration thresholds (primary threshold duration exceeding 10 seconds, intermediate threshold duration exceeding 5 seconds, and advanced threshold duration exceeding 2 seconds), misjudgments caused by brief interference signals can be avoided. Furthermore, in actual applications, the values ​​and duration thresholds for each level can be adjusted and optimized based on different motor types and operating conditions to improve the accuracy and reliability of fault diagnosis.

[0083] (8) Fault Detection: When a motor anomaly is detected, the fault detection process is initiated, and the difference index D and related measured data (such as current and voltage) are input into various fault prediction models. Before inputting the data, feature engineering is performed on the data to extract statistical features and frequency domain features such as the mean, variance, and spectral characteristics of current and voltage. These features are used as input feature vectors for the fault state model to improve the accuracy of fault classification.

[0084] A fault prediction model is constructed for each fault type using a convolutional neural network (CNN). Fault types include rotor eccentricity, stator winding short circuit, permanent magnet demagnetization, bearing fault, and power supply failure. All fault prediction models are stored in a fault model library. Training is performed using a large amount of sample data (no less than 1,000 training samples for each fault type). The CNN network architecture consists of convolutional layers, pooling layers, and fully connected layers. The convolution kernel size is set to 3×3, and the pooling layer uses a max pooling operation with a stride of 2.

[0085] Convolutional and pooling layers extract local and abstract features from the input feature vector, followed by a fully connected layer for fault classification. Training uses a cross-entropy loss function and a stochastic gradient descent (SGD) optimization algorithm. The learning rate is initially set to 0.01, the momentum factor to 0.9, and the number of training iterations is 5000. The input feature vector is passed through a trained CNN classifier to determine the motor fault type and output the fault diagnosis results.

[0086] When training the CNN model, data augmentation techniques are used to increase the number of training samples and improve the model's generalization capabilities. Furthermore, to prevent overfitting, an L2 regularization term (regularization coefficient λ = 0.01) is added to the fully connected layer to constrain the model's weights. In practice, newly collected fault data is regularly used to update and optimize the model to adapt to changes in motor operating conditions and the emergence of new fault types.

[0087] The fault diagnosis method for a permanent magnet synchronous motor provided by the present invention has the following beneficial technical effects:

[0088] (1) Improved diagnostic accuracy: The current and voltage prediction model provided by the present invention comprehensively considers the physical characteristics of the motor and the nonlinear relationship in the actual operating data. Compared with traditional methods, it is more accurate in judging motor abnormalities. A detailed difference index calculation method is adopted, which fully considers the differences between current and voltage on the d-axis and q-axis, and can more comprehensively reflect the degree of deviation between the motor operating status and the model prediction, thereby improving the detection accuracy of motor abnormalities.

[0089] (2) Reduce false alarm rates: The combination of motor physical models and machine learning models (such as long short-term memory networks (LSTMs)) avoids misjudgments caused by the limitations of a single model. The physical model is based on the basic principles of the motor and has basic constraints on normal operating conditions. The machine learning model, by learning complex relationships in large amounts of data, can supplement situations that are difficult for the physical model to handle. The two work together to effectively reduce false alarms caused by a single factor.

[0090] (3) Improved response speed: Real-time monitoring of motor operating parameters, with a short data collection interval (data is collected every 5 milliseconds), enables timely acquisition of the latest motor operating status. Once the difference between the measured data and the model prediction value exceeds the abnormality judgment standard, fault detection is immediately initiated, enabling rapid diagnosis of the fault in a short period of time.

[0091] The present invention has been described exemplarily. Obviously, the specific implementation of the present invention is not limited to the above-mentioned method. As long as various non-substantial improvements are made using the method concept and technical solution of the present invention, or the concept and technical solution of the present invention are directly applied to other occasions without improvement, they are all within the scope of protection of the present invention.

Claims

1. A permanent magnet synchronous motor fault diagnosis method, characterized in that: The method comprises the following steps: (1) Convert the currently collected three-phase current and three-phase voltage into the current and voltage on the d-axis and q-axis; (2) Calculate the theoretical voltage values ​​on the d-axis and q-axis based on the current and voltage on the d-axis and q-axis respectively and Theoretical current value and (3) Based on the theoretical voltage value at the current moment and and operating parameters to obtain the current voltage forecast value and Based on the theoretical current value at the current moment and and operating parameters to obtain the current forecast value at the current moment and (4) performing anomaly detection based on the difference between the voltage prediction value and the current prediction value and the corresponding collected value, and determining the fault type of the motor when an anomaly is detected in the motor; The current theoretical current value The current operating data includes three-phase voltage, three-phase current and motor temperature T, which form an input vector and are input into the trained first LSTM network. The first LSTM network outputs the current prediction value at the current moment. and The current theoretical voltage value and The current operating data includes three-phase voltage, three-phase current and motor temperature T, which form an input vector and are input into the trained second LSTM network. The second LSTM network outputs the voltage prediction value at the current moment. and 2. The permanent magnet synchronous motor fault diagnosis method according to claim 1, characterized in that: The threshold update formula for the first LSTM network or the second LSTM network is as follows: i b =βθ n +(1-β)α[D n -θ n ] Among them, θ n The threshold formed by the last threshold update is also the threshold before this update. n is the difference index after updating based on the running data collected at the current time interval, θ b This is the threshold formed after this update, α is the learning rate, and β is the forgetting factor.

3. The permanent magnet synchronous motor fault diagnosis method according to claim 2, characterized in that: The process of determining the initial value of the threshold is as follows: Based on the difference indicator sequence {D1, D2, ..., D m }Construct the normal distribution probability density function f(D) of the difference index D: According to the maximum likelihood estimation principle, construct the likelihood function L(μ,σ), and determine the estimated values ​​of μ and σ based on the likelihood function L(μ,σ). The initial value of the threshold θ0=μ+3σ, where μ and σ are the parameters of the normal distribution.

4. The permanent magnet synchronous motor fault diagnosis method according to claim 1, characterized in that: Perform anomaly detection on the collected operating data. The outlier detection process is as follows: Determine the i-th running data x based on historical data i The mean μ i and standard deviation σ i , for the currently collected running data x i , judge |x i -μ i |>3σ i Is it true? If so, the currently collected running data x i For outliers, replace them with the average of the adjacent normal values.

5. The permanent magnet synchronous motor fault diagnosis method according to claim 3, characterized in that: The difference index D corresponding to the current running data is calculated based on the following formula: in, It represents the d-axis current and q-axis current obtained by converting the three-phase current collected at the kth moment. It represents the d-axis voltage and q-axis voltage obtained by converting the three-phase voltage collected at the kth moment. They represent the predicted values ​​of d-axis current, q-axis current, d-axis voltage, and q-axis voltage output by the anomaly detection model at the kth moment, respectively, and n represents the total number of the nearest historical sampling points.

6. The permanent magnet synchronous motor fault diagnosis method according to claim 5, characterized in that: The specific process of determining motor abnormality is as follows: When the current difference index D>θ1, and the number of times the difference index D corresponding to the past 10 sampling points is greater than the primary threshold θ1 exceeds 60%, it is determined that the motor is abnormal, where θ1 is set to 0.7 times the current threshold; When the current difference index D>θ2, and the number of times the difference index D corresponding to the past 20 sampling points is greater than the intermediate threshold θ2 exceeds 70%, and the average value of the difference index shows an increasing trend, θ2 is set to 1.1 times the current threshold; When the current difference index D>θ3, and in the past 30 sampling points, the number of times the difference index D is greater than the advanced threshold θ3 exceeds 80%, and the average value of the difference index continues to increase and the increase rate exceeds a set growth threshold, where θ3 is set to 1.3 times the current threshold.

7. The permanent magnet synchronous motor fault diagnosis method according to claim 1, characterized in that: After being determined to be abnormal, the mean, variance and spectral characteristics of the current current and voltage of the motor are input into the fault prediction models of various types of faults, and the current fault type of the motor is determined based on the prediction results output by each fault prediction model.

8. The permanent magnet synchronous motor fault diagnosis method according to claim 7, characterized in that: A fault prediction model is constructed for each type of fault. The fault prediction model is constructed using a convolutional neural network. Fault types include rotor eccentricity, stator winding short circuit, permanent magnet demagnetization, bearing failure, and power supply failure. All fault prediction models are placed in the fault prediction model library.

Images