Motor system fault qualitative diagnosis method based on current sample feature classification analysis

Abstract

The invention discloses a motor system fault qualitative diagnosis method based on current sample feature classification analysis, which comprises the following steps: S1, carrying out multi-point sampling on a current sample of a motor system to obtain an original current signal, and converting the original current signal into a comprehensive current signal; s2, constructing a pre-training data set and a deep learning model, and obtaining a pre-training weight coefficient matrix; s3, fault type, fault degree and fault position information classification is carried out on the fault samples; s4, establishing a fault current vector and a typical fault average current vector; s5, sampling motor current in real time, calculating a fault comprehensive current signal and constructing a fault prediction current vector; and S6, calculating the vector difference between the fault prediction current vector and the typical fault average current vector, and determining the fault type through the minimum value of the vector difference. According to the invention, rapid identification and accurate diagnosis of motor faults can be realized, the method has the advantages of rapid response and strong adaptability, and efficient support is provided for fault diagnosis and maintenance of a motor system.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical signal data processing (G06F), and in particular to a method for qualitatively diagnosing motor system faults based on current sample feature classification analysis. Background Art

[0002] As a key driving device in modern industry, motors play an indispensable role in various mechanical systems. However, during long-term operation, motors will inevitably have some faults. Understanding these common faults and their causes is of great significance for preventing faults, timely repairs, and extending the service life of motors. Motor failures include a series of motor failures caused by motor overheating, motor vibration, motor starting difficulties, and excessive motor noise.

[0003] Motor state monitoring and fault diagnosis technology is a technology that understands and grasps the state of the motor during use, determines whether it is normal or abnormal as a whole or in part, detects faults and their causes early, and can predict the development trend of faults. Motor state monitoring and fault diagnosis technology includes two aspects: identifying motor state monitoring and predicting development trends. In motor fault diagnosis, commonly used methods include signal processing-based methods and machine learning-based methods. Signal processing-based methods require complex preprocessing and analysis of signals, and may not be able to accurately diagnose complex fault types. Machine learning-based methods require a large amount of sample data for training, which not only increases the load on the system, but also may lead to misdiagnosis of some rare fault types. Therefore, a comprehensive and efficient diagnostic method is needed to perform fault characterization and diagnosis on the motor system. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention uses current sample feature classification analysis to perform fault characterization and diagnosis of the motor system. Detection and diagnosis can also be performed when the motor is in working state, which is very convenient and low-cost.

[0005] To achieve the above object, the present invention provides the following technical solution: a motor system fault qualitative diagnosis method based on current sample feature classification analysis, comprising the following steps: S1. Perform multi-point sampling of the current samples of the motor system during operation through multiple sensors to obtain the original current signal, and convert the original current signal into a comprehensive current signal; perform time-sharing sampling of the motor current when the motor fails to obtain a fault current signal; S2, constructing the comprehensive current signal and the fault current signal into a pre-training data set; S3. Establish a deep learning model based on a convolutional neural network, import the processed pre-training data set into the model for training, obtain a pre-training weight coefficient matrix, and complete the construction of the pre-training model; S4, performing qualitative fault classification on the fault samples based on the fault type, fault degree and fault location information; S5, establishing a fault current vector for the fault current signal of the fault sample after the fault qualitative classification, and obtaining a typical fault average current vector; S6. Sample the current of the motor system in real time, obtain the fault sampling current when an unknown fault occurs, calculate the fault comprehensive current signal, use the fault comprehensive current signal as a sample, use the pre-trained model to calculate the fault prediction current, and construct the fault prediction current vector; S7. Calculate the vector difference between the fault prediction current vector and any typical fault average current vector, select a typical fault with the smallest vector difference as the judgment fault, and complete the qualitative fault diagnosis for the motor system.

[0006] Furthermore, the current signal collection in step S1 is specifically as follows: S11, connect the motor driver and connect the current sensor to the power line; S12, collecting current signals, using the sampling circuit and sampling chip in the driver to sample the current signals of the connected current sensors to obtain the original current signals; S13, converting the collected original current signal into a comprehensive current signal, and the conversion formula satisfies: (1) in, Represents the discrete index of the integrated current signal, which is used to refer to the output sampling point calculated by the conversion formula. Represents a discrete index The value of the integrated current signal; represents the sampling index of the original signal, Indicates the sampling index The value of the original current signal; is the imaginary number symbol, is the natural base; S14, sampling the motor current in time when the motor fails to obtain a fault current signal ,satisfy:

[0007] in, Represent the first to N-1th sampling moments respectively.

[0008] Furthermore, in step S2, the pre-training samples are constructed to satisfy: ; in, to They respectively represent the fault current signals collected from the first to the N-1th sampling moments when a motor fault occurs; represents the weight coefficient matrix, which is OK Column matrix, Indicates Line The weight coefficient of the column, and so on.

[0009] Furthermore, in step S5, the fault current vector satisfies: ; in, Indicates Typical fault The fault current vector of samples, Indicates Typical fault Samples in The sampling current at the moment, and so on; The typical fault average current vector satisfies: ; in, Indicates Typical fault average current vector of a typical fault, Indicates The total number of samples of typical faults.

[0010] Furthermore, in step S6, the fault comprehensive current signal is calculated to satisfy: ; in, Indicates the sampling index when an unknown fault occurs The value of the original current signal, Indicates a discrete index when an unknown fault occurs The value of the integrated current signal.

[0011] Further, in step S6, the fault comprehensive current signal is used as a sample and the pre-trained model is used to calculate the fault prediction current to satisfy: ; in, to They respectively represent the fault prediction currents collected from the first to the N-1th sampling moments obtained by the pre-trained model when an unknown fault occurs in the motor; Represents the pre-training weight coefficient matrix, which is OK Column matrix, Indicates Line The pre-trained weight coefficients of the column, and so on.

[0012] Further, in step S6, a fault prediction current vector is constructed to satisfy: ; in, Represents the fault prediction current vector when an unknown fault occurs in the motor.

[0013] Furthermore, the vector difference between the fault prediction current vector and any typical fault average current vector is calculated to satisfy: ; in, The fault prediction current vector when the motor has an unknown fault is The vector difference of the average current vector of typical faults.

[0014] Further, in step S7, a typical fault with the smallest vector difference is selected as a judgment fault that satisfies: ; in, The qualitative fault diagnosis result of the motor unknown fault is shown; Represents the vector difference between the fault prediction current vector and the typical fault average current vector Get the minimum value The fault type.

[0015] Beneficial Effects Compared with the prior art, the present invention provides a motor system fault qualitative diagnosis method based on current sample feature classification analysis, which has the following beneficial effects: 1. Advantages of multi-point sampling and integrated signal conversion: Multi-point sampling of the motor system is performed through multiple sensors and the original current signal is converted into an integrated current signal, making the collected data more comprehensive and accurate. This step ensures that the current signals collected at different parts can be effectively integrated, providing higher signal quality and helping to accurately identify motor fault conditions.

[0016] 2. Pre-training deep learning model to improve diagnostic accuracy: Pre-training of deep learning model based on convolutional neural network enables the model to efficiently identify different types of motor faults, and the learning process of pre-training weight coefficient matrix enhances the model's generalization ability for motor fault patterns. This can significantly improve the accuracy and reliability of the model in actual diagnosis.

[0017] 3. High efficiency of matching fault current vector with typical faults: This solution can quickly identify the fault type of the motor by constructing the vector difference calculation between the fault current vector and the typical fault average current vector. By matching the typical fault with the smallest vector difference, the speed and accuracy of fault qualitative diagnosis are improved, providing an effective basis for timely maintenance.

[0018] 4. Real-time monitoring and fault prediction capabilities: The real-time sampling and fault comprehensive current signal calculation in the solution can capture fault signals immediately when a fault occurs, and predict faults through pre-trained models. This real-time response mechanism makes the system more sensitive and effectively improves the ability to quickly respond to and predict unknown faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0020] In order to better understand the purpose, structure and function of the present invention, the motor system fault qualitative diagnosis method based on current sample feature classification analysis of the present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0021] Example 1 refer to Figure 1 The present invention provides a motor system fault qualitative diagnosis method based on current sample feature classification analysis, comprising the following steps: S1. Perform multi-point sampling of the current samples of the motor system during operation through multiple sensors to obtain the original current signal, and convert the original current signal into a comprehensive current signal; perform time-sharing sampling of the motor current when the motor fails to obtain a fault current signal; S2, constructing the comprehensive current signal and the fault current signal into a pre-training data set; S3. Establish a deep learning model based on a convolutional neural network, import the processed pre-training data set into the model for training, obtain a pre-training weight coefficient matrix, and complete the construction of the pre-training model; S4, performing qualitative fault classification on the fault samples based on the fault type, fault degree and fault location information; S5, establishing a fault current vector for the fault current signal of the fault sample after the fault qualitative classification, and obtaining a typical fault average current vector; S6. Sample the current of the motor system in real time, obtain the fault sampling current when an unknown fault occurs, calculate the fault comprehensive current signal, use the fault comprehensive current signal as a sample, use the pre-trained model to calculate the fault prediction current, and construct the fault prediction current vector; S7. Calculate the vector difference between the fault prediction current vector and any typical fault average current vector, select a typical fault with the smallest vector difference as the judgment fault, and complete the qualitative fault diagnosis for the motor system.

[0022] The current signal acquisition in step S1 is specifically as follows: S11, connect the motor driver and connect the current sensor to the power line; S12, collecting current signals, using the sampling circuit and sampling chip in the driver to sample the current signals of the connected current sensors to obtain the original current signals; S13, converting the collected original current signal into a comprehensive current signal, and the conversion formula satisfies: ; (1) in, Represents the discrete index of the integrated current signal, which is used to refer to the output sampling point calculated by the conversion formula. Represents a discrete index The value of the integrated current signal; represents the sampling index of the original signal, Indicates the sampling index The value of the original current signal; is the imaginary number symbol, is the natural base; S14, sampling the motor current in time when the motor fails to obtain a fault current signal ,satisfy:

[0023] in, Represent the first to N-1th sampling moments respectively.

[0024] In step S2, construct pre-training samples to meet the following requirements: ; in, to They respectively represent the fault current signals collected from the first to the N-1th sampling moments when a motor fault occurs; represents the weight coefficient matrix, which is OK Column matrix, Indicates Line The weight coefficient of the column, and so on.

[0025] In step S5, the fault current vector satisfies: ; in, Indicates Typical fault The fault current vector of samples, Indicates Typical fault Samples in The sampling current at the moment, and so on; The typical fault average current vector satisfies: ; in, Indicates Typical fault average current vector of a typical fault, Indicates The total number of samples of typical faults.

[0026] In step S6, the fault comprehensive current signal is calculated to satisfy:

[0027] in, Indicates the sampling index when an unknown fault occurs The value of the original current signal, Indicates a discrete index when an unknown fault occurs The value of the integrated current signal.

[0028] In step S6, the fault comprehensive current signal is used as a sample and the pre-trained model is used to calculate the fault prediction current to satisfy:

[0029] in, to They respectively represent the fault prediction currents collected from the first to the N-1th sampling moments obtained by the pre-trained model when an unknown fault occurs in the motor; Represents the pre-training weight coefficient matrix, which is OK Column matrix, Indicates Line The pre-trained weight coefficients of the column, and so on.

[0030] In step S6, a fault prediction current vector is constructed to satisfy:

[0031] in, Represents the fault prediction current vector when an unknown fault occurs in the motor.

[0032] The vector difference between the fault prediction current vector and any typical fault average current vector satisfies:

[0033] in, The fault prediction current vector when the motor has an unknown fault is The vector difference of the average current vector of typical faults.

[0034] In step S7, a typical fault with the smallest vector difference is selected as a judgment fault that satisfies:

[0035] in, The qualitative fault diagnosis result of the motor unknown fault is shown; Represents the vector difference between the fault prediction current vector and the typical fault average current vector Get the minimum value The fault type.

[0036] Specifically, motor failures can be divided into many types, including bearing failure, insulation aging, winding failure, brush wear, overload and overheating, fan failure, etc. These failures not only affect the normal operation of the motor, but may also cause more serious damage; The fault location and specific reasons include: 1. The bearing operating temperature is too high: This may be due to the wrong brand of lubricating oil, deterioration, too much or too little lubricating oil, bearing wear, rust, pitting, inner sleeve or outer sleeve running, poor assembly of inner and outer covers or oil retaining rings, coupling misalignment or belt overtightening, etc.

[0037] 2. "Excessive temperature or smoke": This may be due to power supply problems, such as too high or too low voltage or phase loss; motor problems, such as short circuit or grounding between phases or turns of the stator winding, broken rotor bars or friction between the stator and rotor; load problems, such as excessive mechanical load or jamming; ventilation and heat dissipation problems, such as high ambient temperature, excessive sludge on the casing, clogged air duct, damaged or reversely installed fan, etc.

[0038] 3. Abnormal noise or strong vibration: It may be due to the friction between the stator and rotor or the serious wear and deformation of the towed machinery, uneven foundation, weak foundation or loose foundation screws, misaligned coupling or bent shaft, eccentric or unbalanced rotor, lack of oil or damage of bearings, etc.

[0039] Example 2 The present invention also provides a motor system fault qualitative diagnosis method based on current sample feature classification analysis, and its process is as follows: 1) Current signal acquisition: Use sensors to collect current and voltage data when the motor is running. These data will be used for subsequent feature extraction and diagnosis. The current signal acquisition is specifically as follows: First, connect the motor driver and correctly connect the current sensor to the power line; Secondly, collect current signals, and use the analog circuit and sampling chip in the driver to collect and convert the current signals of the connected current sensor; Finally, after the acquired current signal is converted into digital form, data processing and analysis can be performed.

[0040] It should be noted that the sensor also collects voltage data and temperature data of the motor, and is applied to the diagnosis of current faults based on the characteristics of multi-source data fusion. According to the extraction of multi-source data fusion features, faults are identified and predicted through artificial intelligence models and methods.

[0041] 2) Data preprocessing: preprocessing the collected current data, including noise removal, normalization and other operations, to ensure the accuracy and reliability of the data and obtain a sample data set; Specifically include: Data cleaning, including processing missing values ​​and outliers. Missing values ​​can be processed by deletion, replacement or interpolation. Outliers can be identified and processed through statistical and machine learning methods. Data integration, merging data from different sources together, requires resolving data conflicts and inconsistencies; ‌Data reduction, compressing data through algorithms or using clustering methods to reduce the dimensionality of data to improve processing efficiency and accuracy‌. ‌

[0042] Furthermore, the preprocessing also includes obtaining the stator current signal, reconstructing the noise signal, and then subtracting the reconstructed signal from the original stator current signal to obtain the residual current. The noise signal reconstruction formula is: r(t)=s(t)+n(t) Among them, r(t) is the reconstructed signal, s(t) is the original signal, and n(t) is the noise signal.

[0043] 3) Building a deep learning model Based on convolutional neural network (CNN), CNN can identify abnormal patterns in current data and reduce false positives and negatives by optimizing the model. By analyzing the morphological characteristics of current data, intelligent diagnosis of motor faults can be achieved.

[0044] The neural network algorithm diagnoses the normal and various abnormal conditions of the motor, including: bearing damage, inter-turn short circuit, rotor bar breakage, fault diagnosis and other problems.

[0045] Deep learning models require a large number of labeled samples for training, so fault samples need to be labeled.

[0046] As a non-intrusive diagnostic method, the motor current purely reflects the operation of the motor. Fault diagnosis based on motor current signature analysis (MCSA) has the following advantages: a) the current signal is easy to collect, just pass the power line through the current sensor; b) signal acquisition does not interfere with system operation; c) the collected signal is robust to environmental noise; d) the current sensor is cheap.

[0047] 4) Fault feature extraction Specifically, firstly, simulation is set up in SIMULINK to obtain fault data, and then fault diagnosis is performed based on signal processing feature extraction and classification recognition algorithm; The working principle of the motor is essentially the interaction between electricity and magnetism. When the motor is abnormal, the original electromagnetic balance will be broken, and the fault characteristics will be fed back to the stator circuit in the form of specific harmonics. Motor fault monitoring based on current characteristic analysis is to identify the characteristic signals related to motor faults in the spectrum by analyzing the motor current signal.

[0048] This embodiment is carried out in a preprocessing manner. First, data preprocessing is an important step in fault feature extraction. The raw data needs to be cleaned, outliers and noise removed, etc. to ensure the accuracy and reliability of the data. This step can be performed using tools such as MATLAB and Python.

[0049] 5) Fault type identification and diagnosis Through the trained deep learning model, the motor signal can be used to identify and locate faults. According to the characteristics of the input signal, the model can determine whether the motor has a fault and locate the specific location of the fault. In addition, the deep learning-based method can also realize fault diagnosis and prediction. By analyzing the signal characteristics generated when the motor fails, the cause of the fault can be diagnosed and possible future faults can be predicted.

[0050] Others diagnose the cause and extent of motor failure by detecting the load current amplitude and waveform and performing spectrum analysis. For example, by detecting the motor current and performing spectrum analysis, it can be used to diagnose whether the motor has defects such as broken rotor winding bars, eccentric air gaps, stator winding failures, and rotor imbalance.

[0051] Furthermore, it also includes using a classifier to perform qualitative diagnosis of motor faults: by building a simulation model and training with actual data, CNN can learn the characteristic representation of the fault, thereby realizing fault diagnosis.

[0052] The core advantage of the motor system fault qualitative diagnosis method based on current sample feature classification analysis of the present invention lies in its high efficiency and accuracy. This method can monitor the health status of the motor in real time by analyzing the current signal when the motor is running, and give an early warning before a fault occurs, thereby improving the reliability and safety of the motor operation.

[0053] It is to be understood that the present invention is described by some embodiments, and it is known to those skilled in the art that various changes or equivalent substitutions may be made to these features and embodiments without departing from the spirit and scope of the present invention. In addition, under the teachings of the present invention, these features and embodiments may be modified to adapt to specific circumstances and materials without departing from the spirit and scope of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the scope of protection of the present invention.

Claims

1. A motor system fault qualitative diagnosis method based on current sample feature classification analysis, characterized in that: The following steps are involved: S1. Obtaining a comprehensive current signal and a fault current signal: performing multi-point sampling of current samples of the motor system during operation through multiple sensors to obtain an original current signal, and converting the original current signal into a comprehensive current signal; Perform time-sharing sampling on the motor current when the motor fails to generate a fault current signal; S2, constructing the comprehensive current signal and the fault current signal into a pre-training data set; S3. Complete the construction of the pre-training model based on the pre-training data set: establish a deep learning model based on the convolutional neural network, import the processed pre-training data set into the model for training, obtain the pre-training weight coefficient matrix, and complete the construction of the pre-training model; S4. Complete fault qualitative classification: perform fault qualitative classification on the fault samples based on fault type, fault degree and fault location information; S5. Obtaining a typical fault average current vector: establishing a fault current vector for the fault current signal of the fault sample after the fault qualitative classification, and obtaining a typical fault average current vector; S6. Constructing a fault prediction current vector: sampling the current of the motor system in real time, obtaining a fault sampling current when an unknown fault occurs, calculating a fault comprehensive current signal, using the fault comprehensive current signal as a sample, using a pre-trained model to calculate a fault prediction current, and constructing a fault prediction current vector; S7. Complete qualitative fault diagnosis for the motor system: calculate the vector difference between the fault prediction current vector and any typical fault average current vector, select a typical fault with the smallest vector difference as the judgment fault, and complete qualitative fault diagnosis for the motor system.

2. The motor system fault qualitative diagnosis method based on current sample feature classification analysis according to claim 1 is characterized in that: The current signal acquisition in step S1 is specifically as follows: S11, connect the motor driver and connect the current sensor to the power line; S12, collecting current signals, using the sampling circuit and sampling chip in the driver to sample the current signals of the connected current sensors to obtain the original current signals; S13, converting the collected original current signal into a comprehensive current signal, and the conversion formula satisfies: ； （1） in, Represents the discrete index of the integrated current signal, which is used to refer to the output sampling point calculated by the conversion formula. Represents a discrete index The value of the integrated current signal; represents the sampling index of the original signal, Indicates the sampling index The value of the original current signal; is the imaginary number symbol, is the natural base; S14, sampling the motor current in time when the motor fails to obtain a fault current signal ,satisfy: ； in, Represent the first to N-1th sampling moments respectively.

3. The motor system fault qualitative diagnosis method based on current sample feature classification analysis according to claim 1 is characterized in that: In step S2, construct pre-training samples to meet the following requirements: ； in, to They respectively represent the fault current signals collected from the first to the N-1th sampling moments when a motor fault occurs; represents the weight coefficient matrix, which is OK Column matrix, Indicates Line The weight coefficient of the column, and so on.

4. The motor system fault qualitative diagnosis method based on current sample feature classification analysis according to claim 1 is characterized in that: In step S5, the fault current vector satisfies: ； in, Indicates Typical fault The fault current vector of samples, Indicates Typical fault Samples in The sampling current at the moment, and so on; The typical fault average current vector satisfies: ； in, Indicates Typical fault average current vector of a typical fault, Indicates The total number of samples of typical faults.

5. The motor system fault qualitative diagnosis method based on current sample feature classification analysis according to claim 4 is characterized in that: In step S6, the fault comprehensive current signal is calculated to satisfy: ； in, Indicates the sampling index when an unknown fault occurs The value of the original current signal, Indicates a discrete index when an unknown fault occurs The value of the integrated current signal.

6. The motor system fault qualitative diagnosis method based on current sample feature classification analysis according to claim 5 is characterized in that: In step S6, the fault comprehensive current signal is used as a sample and the pre-trained model is used to calculate the fault prediction current to satisfy: ； in, to They respectively represent the fault prediction currents collected from the first to the N-1th sampling moments obtained by the pre-trained model when an unknown fault occurs in the motor; Represents the pre-training weight coefficient matrix, which is OK Column matrix, Indicates Line The pre-trained weight coefficients of the column, and so on.

7. The motor system fault qualitative diagnosis method based on current sample feature classification analysis according to claim 6 is characterized in that: In step S6, a fault prediction current vector is constructed to satisfy: ； in, Represents the fault prediction current vector when an unknown fault occurs in the motor.

8. The motor system fault qualitative diagnosis method based on current sample feature classification analysis according to claim 7 is characterized in that: In step S7, the vector difference between the fault prediction current vector and any typical fault average current vector is calculated to satisfy: ； in, The fault prediction current vector when the motor has an unknown fault is The vector difference of the average current vector of typical faults.

9. The motor system fault qualitative diagnosis method based on current sample feature classification analysis according to claim 7, characterized in that: In step S7, a typical fault with the smallest vector difference is selected as a judgment fault that satisfies: ； in, The qualitative fault diagnosis result of the motor unknown fault is shown; Represents the vector difference between the fault prediction current vector and the typical fault average current vector Get the minimum value The fault type.

Images