CN115877205A - Intelligent fault diagnosis system and method for servo motor - Google Patents
Intelligent fault diagnosis system and method for servo motor Download PDFInfo
- Publication number
- CN115877205A CN115877205A CN202211535222.4A CN202211535222A CN115877205A CN 115877205 A CN115877205 A CN 115877205A CN 202211535222 A CN202211535222 A CN 202211535222A CN 115877205 A CN115877205 A CN 115877205A
- Authority
- CN
- China
- Prior art keywords
- motor
- module
- fault
- support vector
- vector machine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Control Of Electric Motors In General (AREA)
Abstract
The invention discloses an intelligent fault diagnosis system and method of a servo motor, belonging to the technical field of servo motors and comprising an acquisition module, a preprocessing module, a training module, a sample optimization module, a quantum state description module, a diagnosis output module, a data storage module, a sign extraction module and a support vector machine diagnosis module; the collection module enables the motor to operate in a specified operation mode, real-valued samples of the motor to be tested are described through a quantum state, hidden layer Euclidean distance calculation is replaced by quantum state similarity coefficients, a preset motor fault diagnosis model is utilized, the real-valued samples of the motor to be tested are classified, fault diagnosis of the motor is achieved, and manual routing inspection or an analysis model is not needed; the diagnosis process is simple, the limitation that the traditional diagnosis method depends on manual inspection or analysis of a model is broken through, and the accuracy of the fault diagnosis algorithm is effectively improved.
Description
Technical Field
The invention relates to the technical field of servo motors, in particular to a fault intelligent diagnosis system of a servo motor and a diagnosis method thereof.
Background
In the modern society, with the continuous progress of science and technology and the rapid development of economy, the motor is widely applied to various fields of production and life as an important driving device, and plays an irreplaceable role in modern construction and industrial manufacturing. Once a motor fails during operation, a series of chain reactions can be caused, so that the whole industrial process is stopped, the production efficiency is influenced, and even the loss of life and property can be caused. Therefore, the development of the motor fault diagnosis technology is beneficial to ensuring the safety and stable operation of the power equipment, the effective management and maintenance of the motor are realized, and the benefit of the driving equipment is greatly improved.
The prior art also has the following defects:
(1) The traditional motor fault diagnosis method is usually carried out based on an analytic model, and the analytic model is established for a system to be diagnosed by using a certain logic language according to the relation among various state parameters of the system. The method requires establishing an accurate mathematical relationship, selects appropriate state parameters and statistical decisions, and has the advantages of large limitation, high complexity and low precision in practical application.
(2) The traditional motor fault diagnosis system can only diagnose whether the motor is in fault, cannot distinguish fault types, cannot learn new fault types, and can classify new faults; on the other hand, the conventional motor failure diagnosis system can only perform failure diagnosis, and cannot predict the failure occurrence time of the motor based on the past test data.
(3) Meanwhile, when the fault characteristics of the motor are relatively obvious, the traditional method can obtain a relatively good diagnosis effect; when the fault of the motor is slight, the fault diagnosis accuracy of the traditional method is reduced to a certain extent.
Disclosure of Invention
The invention aims to provide an intelligent fault diagnosis system and a diagnosis method for a servo motor, which aim to solve the problem that the traditional motor fault diagnosis method provided in the background art is generally carried out based on an analysis model, and the analysis model is established for a system to be diagnosed by using a certain logic language according to the relation between various state parameters of the system. The method requires establishing an accurate mathematical relationship, selects appropriate state parameters and statistical decisions, and has the advantages of large limitation, high complexity and low precision in practical application; the traditional motor fault diagnosis system can only diagnose whether the motor is in fault, cannot distinguish fault types, cannot learn new fault types, and can classify new faults; on the other hand, the conventional motor fault diagnosis system can only carry out fault diagnosis and cannot predict the fault occurrence period of the motor according to the conventional test data; meanwhile, when the fault characteristics of the motor are relatively obvious, the traditional method can obtain a relatively good diagnosis effect; when the fault of the motor is slight, the fault diagnosis accuracy rate of the traditional method has the problem of reducing to a certain degree.
The technical scheme of the invention is as follows: the device comprises an acquisition module, a signal monitoring module, a preprocessing module, a training module, a sample optimization module, a quantum state description module, a diagnosis output module, a fault diagnosis module, a data storage module, a data acquisition module, a sign extraction module and a support vector machine diagnosis module;
the acquisition module is used for measuring the vibration signal of the motor and outputting calibration data to the preprocessing module while enabling the motor to operate in a specified operation mode, measuring the vibration signal of the motor while enabling the motor to operate in the specified operation mode again after the motor operates, and outputting test data to the preprocessing module for acquiring a time sequence signal of the motor to be tested;
the signal monitoring module is used for judging whether the fault alarm signal is monitored or not;
the preprocessing module is used for carrying out noise reduction processing on the data acquired by the acquisition module, carrying out time domain analysis on the noise-reduced signals to obtain time domain indexes and constructing a characteristic matrix;
the sign extraction module is used for collecting stator current of the motor, performing Hilbert series transformation on the stator current, performing Fourier decomposition on a transformation result, and extracting a characteristic frequency component of the fault to be diagnosed;
the system is used for respectively collecting stator currents of a motor which normally operates and different fault motors, carrying out Hilbert series transformation on the stator currents, carrying out Fourier decomposition on a transformation result, and extracting fault characteristic frequency components for constructing a model;
the fault characteristic frequency components used for building the model comprise frequency components of multiple fundamental wave frequencies of two times and multiple fundamental wave frequencies of three times corresponding to motor structure asymmetry caused by faults;
the training module uses the calibration data processed by the preprocessing module as a training sample for training a one-class support vector machine method, and stores a normal area of a mapping space for generating the one-class support vector machine method into the data storage module; using the test data processed by the preprocessing module as additional calibration data, and constructing a plurality of two classifiers by using a two-classification support vector machine method to generate new abnormal areas of a mapping space and store the new abnormal areas in a data storage module;
the data storage module is used for storing the normal area and the abnormal area of the mapping space of the training module;
the data acquisition module is used for acquiring the voltage of the storage battery of the external storage battery connected with the motor in a cold machine state or a heat machine state respectively if the fault alarm signal is monitored, wherein the heat machine state is a state after the generator is kept stand at a preset temperature for a preset time;
the fault diagnosis module is used for judging whether the voltage of the corresponding motor bottle is greater than the regulation protection voltage of the voltage regulator, and if so, determining that the voltage of the motor bottle is greater than the regulation protection voltage as a trigger factor of the fault alarm signal.
The support vector machine diagnosis module is used for inputting the characteristic frequency component of the fault to be diagnosed into an optimal support vector machine diagnosis model to diagnose the fault of the motor, evaluating the health degree of the motor, and outputting the fault category if the motor has the fault; the support vector machine diagnosis model building module is used for building an optimal support vector machine diagnosis model and setting the optimal support vector machine diagnosis model in the support vector machine diagnosis module;
the sample module is used for constructing a support vector machine diagnosis model sample based on the fault characteristic frequency component for constructing the model, and is used for carrying out time-frequency transformation on the time sequence signal of the motor to be tested to obtain an energy characteristic index of the time sequence signal as a real value sample of the motor to be tested;
the sample optimization module is used for optimizing core parameters in the support vector machine diagnosis model by adopting a grid search method or a genetic algorithm or a particle swarm algorithm to obtain an optimal support vector machine diagnosis model;
the diagnosis output module compares newly-increased data of motor operation with data of the data storage module, diagnoses by using a first-class support vector machine method and a plurality of second classifiers, is used for inputting real-value samples of quantum state description into a preset motor fault diagnosis model, and outputs the fault diagnosis result of the motor to be tested;
the quantum state description module is used for carrying out quantum state description on the real-value sample of the motor to be tested to obtain the real-value sample of the quantum state description.
Further, the denoising processing method is singular value decomposition, and the time domain indexes are energy, kurtosis and mean square value.
Further, the diagnosis output module diagnoses the motor as normal when the test data is included in the normal region, and diagnoses the motor as abnormal when the test data is not included in the normal region.
Furthermore, the support vector machine diagnosis model is a C-SVC model, and the kernel function is an RBF kernel function; the core parameter of the support vector machine diagnosis model is a penalty factor of the C-SVC model; the core parameter of the RBF kernel function is a weight factor of the kernel function.
An intelligent fault diagnosis method for a servo motor comprises the following steps:
monitoring the fault alarm signal through a signal monitoring module, and judging whether the fault alarm signal is monitored;
if yes, respectively obtaining the voltage connected with the motor in a cold machine state or a heat machine state, wherein the heat machine state is a state after the motor is kept stand at a preset temperature for a preset time; judging whether the corresponding motor is larger than the regulation protection voltage of the voltage regulator, if so, determining that the motor is larger than the regulation protection voltage as a triggering factor of the fault alarm signal; if the fault alarm signal is not monitored and the motor is in the cold machine state or the hot machine state respectively, determining that the temperature is not an initiating factor of the fault alarm signal;
step two, acquiring a time sequence signal of the motor to be tested, calibrating, measuring a vibration signal of the motor to acquire calibration data while enabling the motor to operate in a specified operation mode by a data acquisition module, and transmitting the calibration data to a preprocessing module;
collecting stator current of a motor, performing Hilbert series transformation on the stator current, performing Fourier decomposition on a transformation result, and extracting a characteristic frequency component of a fault to be diagnosed;
performing time-frequency transformation on the time sequence signal of the motor to be tested to obtain an energy characteristic index of the time sequence signal, taking the energy characteristic index as a real-value sample of the motor to be tested, performing noise reduction processing on the acquired data by using a preprocessing module, performing time domain analysis on the noise-reduced signal to obtain a time domain index, and constructing a characteristic matrix;
inputting the characteristic frequency component of the fault to be diagnosed into an optimal support vector machine diagnosis model to diagnose the fault of the motor, evaluating the health degree of the motor, and outputting the fault category if the motor has the fault;
performing quantum state description on a real-value sample of the motor to be tested to obtain the real-value sample of the quantum state description, measuring a motor vibration signal to obtain test data while operating the motor in the specified operation mode again after the motor is operated, and performing signal processing on the test data by using the preprocessing procedure to construct a feature matrix;
inputting the real-value sample of the quantum state description into a preset motor fault diagnosis model, outputting the fault diagnosis result of the motor to be tested, generating a working procedure, and generating a normal region of a mapping space of a support vector machine method by using the calibration data as exercise data; using the test data as additional calibration data, and constructing a plurality of two classifiers by using a two-classification support vector machine method to generate a new abnormal region of a mapping space; storing the normal area and the abnormal area in a data storage module;
and seventhly, diagnosing the newly added data of the motor operation and the data of the data storage module by the diagnosis output module, specifically, distinguishing normal data and abnormal data by using a first-class support vector machine method, and classifying the newly added abnormal data by using a second-class support vector machine method, wherein the first-class support vector machine method can predict the service life of the motor.
Furthermore, the time sequence signals of the motor to be tested comprise three-axis acceleration signals, current signals and voltage signals when the motor to be tested runs.
Further, the process of performing time-frequency transformation on the time sequence signal of the motor to be tested to obtain the energy characteristic index of the time sequence signal is as follows:
and performing time-frequency transformation on the time sequence signal of the motor to be tested by adopting an improved empirical mode decomposition method to obtain an energy characteristic index of the time sequence signal.
Further, the method for constructing the optimal support vector machine diagnosis model comprises the following steps:
respectively collecting stator currents of a motor which normally operates and different fault motors, carrying out Hilbert series transformation on the stator currents, carrying out Fourier decomposition on transformation results, and extracting fault characteristic frequency components for constructing a model;
the fault characteristic frequency components used for constructing the model comprise frequency components of multiple fundamental wave frequencies corresponding to two times and three times of asymmetry of a motor structure caused by faults;
constructing a support vector machine diagnosis model based on the fault characteristic frequency component for constructing the model; optimizing core parameters in the support vector machine diagnosis model by adopting a grid search method or a genetic algorithm or a particle swarm algorithm to obtain an optimal support vector machine diagnosis model;
the core parameters are parameters influencing the optimal objective function performance of the support vector machine diagnosis model.
The invention provides a fault intelligent diagnosis system of a servo motor and a diagnosis method thereof through improvement, compared with the prior art, the fault intelligent diagnosis system has the following improvements and advantages:
firstly, describing a real-valued sample of a motor to be tested through a quantum state, replacing hidden layer Euclidean distance calculation with a quantum state similarity coefficient, classifying the real-valued sample of the motor to be tested by utilizing a preset motor fault diagnosis model, and realizing fault diagnosis of the motor without depending on manual inspection or an analysis model; the diagnosis process is simple, the limitation that the traditional diagnosis method depends on manual inspection or analysis of a model is broken through, and the accuracy of the fault diagnosis algorithm is effectively improved.
The invention can realize the diagnosis of the motor normality or not, identify the motor fault type and predict the motor fault period.
Thirdly, on the basis of the characteristic frequency of the existing stator current fault, the characteristic frequency component of the stator current corresponding to the motor structure asymmetry caused by the fault is additionally considered, namely the frequency components of the fundamental wave frequency of multiples of two and multiples of three; amplifying the fault frequency component by using Hilbert transform and separating the fault frequency component from the fundamental frequency component; the diagnostic sensitivity is improved by adopting a support vector machine method, and the core parameters of a support vector machine diagnostic model are optimized through a grid search algorithm, a particle swarm algorithm and a genetic algorithm; the problem that the diagnosis accuracy rate of the traditional method is reduced when the induction motor has slight faults is effectively solved.
Drawings
The invention is further explained below with reference to the figures and examples:
FIG. 1 is a block diagram of a fault intelligent diagnosis system of a servo motor and a diagnosis method thereof;
Detailed Description
The present invention will be described in detail below with reference to the attached drawings, and the technical solutions in the embodiments of the present invention will be clearly and completely described. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a fault intelligent diagnosis system of a servo motor and a diagnosis method thereof through improvement, and the fault intelligent diagnosis system comprises an acquisition module, a signal monitoring module, a preprocessing module, a training module, a sample optimizing module, a quantum state description module, a diagnosis output module, a fault diagnosis module, a data storage module, a data acquisition module, a sign extraction module and a support vector machine diagnosis module;
the acquisition module is used for measuring the vibration signal of the motor and outputting calibration data to the preprocessing module while enabling the motor to operate in a specified operation mode, measuring the vibration signal of the motor while enabling the motor to operate in the specified operation mode again after the motor operates, and outputting test data to the preprocessing module for acquiring a time sequence signal of the motor to be tested;
the signal monitoring module is used for judging whether a fault alarm signal is monitored or not;
the preprocessing module is used for carrying out noise reduction processing on the data acquired by the acquisition module, carrying out time domain analysis on the noise-reduced signals to obtain time domain indexes and constructing a characteristic matrix;
the sign extraction module is used for collecting stator current of the motor, performing Hilbert series transformation on the stator current, performing Fourier decomposition on a transformation result, and extracting a characteristic frequency component of the fault to be diagnosed;
the system is used for respectively collecting stator currents of a motor which normally operates and different fault motors, carrying out Hilbert series transformation on the stator currents, carrying out Fourier decomposition on a transformation result, and extracting fault characteristic frequency components for constructing a model;
the fault characteristic frequency components used for building the model comprise frequency components of multiple fundamental wave frequencies of two times and multiple fundamental wave frequencies of three times corresponding to motor structure asymmetry caused by faults;
the training module is used for using the calibration data processed by the preprocessing module as a training sample for training a one-class support vector machine method and storing a normal area of a mapping space for generating the one-class support vector machine method into the data storage module; using the test data processed by the preprocessing module as additional calibration data, and constructing a plurality of two classifiers by using a two-classification support vector machine method to generate new abnormal areas of the mapping space and store the new abnormal areas in a data storage module;
the data storage module is used for storing a normal area and an abnormal area of the mapping space of the training module;
the data acquisition module is used for acquiring the voltage of a storage battery of an external storage battery connected with the motor in a cold machine state or a heat machine state respectively if a fault alarm signal is monitored, wherein the heat machine state is a state after the generator is kept stand at a preset temperature for a preset time;
and the fault diagnosis module is used for judging whether the voltage of the corresponding motor bottle is greater than the regulation protection voltage of the voltage regulator, and if so, determining that the voltage of the motor is greater than the regulation protection voltage as a triggering factor of the fault alarm signal.
The support vector machine diagnosis module is used for inputting the characteristic frequency component of the fault to be diagnosed into the optimal support vector machine diagnosis model to diagnose the fault of the motor, evaluating the health degree of the motor, and outputting the fault category if the motor has the fault; the support vector machine diagnosis model building module is used for building an optimal support vector machine diagnosis model and setting the optimal support vector machine diagnosis model in the support vector machine diagnosis module;
the system comprises a sample module, a fault characteristic frequency component generation module, a fault characteristic frequency component analysis module and a fault characteristic frequency component analysis module, wherein the sample module is used for constructing a support vector machine diagnosis model sample based on the fault characteristic frequency component used for constructing the model, and is used for carrying out time-frequency transformation on a time sequence signal of a motor to be tested to obtain an energy characteristic index of the time sequence signal as a real-value sample of the motor to be tested;
the sample optimization module is used for optimizing core parameters in the support vector machine diagnosis model by adopting a grid search method or a genetic algorithm or a particle swarm algorithm to obtain an optimal support vector machine diagnosis model;
the diagnosis output module is used for comparing newly-increased data of the motor operation with data of the data storage module, diagnosing by using a first-class support vector machine method and a plurality of second classifiers, inputting a real-value sample of the quantum state description into a preset motor fault diagnosis model, and outputting to obtain a fault diagnosis result of the motor to be tested;
and the quantum state description module is used for carrying out quantum state description on the real-value sample of the motor to be tested to obtain the real-value sample of the quantum state description.
The noise reduction processing method is singular value decomposition, and the time domain indexes are energy, kurtosis and mean square value.
The diagnosis output module diagnoses the motor as normal when the test data is contained in the normal region, and diagnoses the motor as abnormal when the test data is not contained in the normal region.
The support vector machine diagnosis model is a C-SVC model, and the kernel function is an RBF kernel function; the core parameter of the support vector machine diagnosis model is a penalty factor of the C-SVC model; the core parameter of the RBF kernel function is a weight factor of the kernel function.
An intelligent fault diagnosis method for a servo motor comprises the following steps:
monitoring a fault alarm signal through a signal monitoring module, and judging whether the fault alarm signal is monitored;
if yes, respectively obtaining the voltage connected with the motor in a cold machine state or a heat machine state, wherein the heat machine state is a state after the motor is kept stand at a preset temperature for a preset time; judging whether the corresponding motor is larger than the regulation protection voltage of the voltage regulator, if so, determining that the motor is larger than the regulation protection voltage as a triggering factor of the fault alarm signal; if the fault alarm signal is not monitored and the motor is respectively in a cold machine state or a hot machine state, determining that the temperature is not a triggering factor of the fault alarm signal;
step two, acquiring a time sequence signal of the motor to be tested, calibrating, measuring a vibration signal of the motor to acquire calibration data while enabling the motor to operate in a specified operation mode by a data acquisition module, and transmitting the calibration data to a preprocessing module;
collecting stator current of a motor, performing Hilbert series transformation on the stator current, performing Fourier decomposition on a transformation result, and extracting a characteristic frequency component of a fault to be diagnosed;
performing time-frequency transformation on the time sequence signal of the motor to be tested to obtain an energy characteristic index of the time sequence signal, taking the energy characteristic index as a real-value sample of the motor to be tested, performing noise reduction processing on the acquired data by using a preprocessing module, performing time domain analysis on the noise-reduced signal to obtain a time domain index, and constructing a characteristic matrix;
inputting the characteristic frequency component of the fault to be diagnosed into an optimal support vector machine diagnosis model to diagnose the fault of the motor, evaluating the health degree of the motor, and outputting the fault category if the motor has the fault;
step five, carrying out quantum state description on the real value sample of the motor to be tested to obtain the real value sample of the quantum state description, and carrying out a testing procedure, wherein after the motor is operated, the motor is operated in a specified operation mode again, the motor vibration signal is measured to obtain testing data, and the testing data is subjected to signal processing by using a preprocessing procedure to construct a characteristic matrix;
inputting the real-value sample of the quantum state description into a preset motor fault diagnosis model, outputting the fault diagnosis result of the motor to be tested, generating a working procedure, and generating a normal region of a mapping space of a support vector machine method by using calibration data as exercise data; using the test data as additional calibration data, and constructing a plurality of two classifiers by using a two-classification support vector machine method to generate an abnormal region of a new mapping space; storing the normal area and the abnormal area in a data storage module;
and seventhly, the diagnosis output module diagnoses the newly added data of the motor operation and the data of the data storage module, specifically, a first-class support vector machine method is used for distinguishing normal data and abnormal data, and a second-class support vector machine method is used for classifying the newly added abnormal data, wherein the first-class support vector machine method can predict the service life of the motor.
The time sequence signals of the motor to be tested comprise three-axis acceleration signals, current signals and voltage signals when the motor to be tested runs.
The process of performing time-frequency transformation on the time sequence signal of the motor to be tested to obtain the energy characteristic index of the time sequence signal specifically comprises the following steps:
and performing time-frequency transformation on the time sequence signal of the motor to be tested by adopting an improved empirical mode decomposition method to obtain an energy characteristic index of the time sequence signal.
The method for constructing the optimal support vector machine diagnosis model comprises the following steps:
respectively collecting stator currents of a motor which normally operates and different fault motors, carrying out Hilbert series transformation on the stator currents, carrying out Fourier decomposition on transformation results, and extracting fault characteristic frequency components for constructing a model;
the fault characteristic frequency components used for constructing the model comprise frequency components of multiple fundamental wave frequencies corresponding to two times and three times of asymmetry of a motor structure caused by faults;
constructing a support vector machine diagnosis model based on the fault characteristic frequency component for constructing the model; optimizing core parameters in the support vector machine diagnosis model by adopting a grid search method or a genetic algorithm or a particle swarm algorithm to obtain an optimal support vector machine diagnosis model;
the core parameters are parameters influencing the optimal objective function performance of the support vector machine diagnosis model.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The intelligent fault diagnosis system of the servo motor is characterized by comprising an acquisition module, a signal monitoring module, a preprocessing module, a training module, a sample optimization module, a quantum state description module, a diagnosis output module, a fault diagnosis module, a data storage module, a data acquisition module, a sign extraction module and a support vector machine diagnosis module;
the acquisition module is used for measuring a vibration signal of the motor and outputting calibration data to the preprocessing module while enabling the motor to operate in a specified operation mode, and measuring the vibration signal of the motor and outputting test data to the preprocessing module while enabling the motor to operate in the specified operation mode again after the motor operates, so as to obtain a time sequence signal of the motor to be tested;
the signal monitoring module is used for judging whether the fault alarm signal is monitored or not;
the preprocessing module is used for carrying out noise reduction processing on the data acquired by the acquisition module, carrying out time domain analysis on the noise-reduced signals to obtain time domain indexes and constructing a characteristic matrix;
the sign extraction module is used for collecting stator current of the motor, performing Hilbert series transformation on the stator current, performing Fourier decomposition on a transformation result, and extracting a characteristic frequency component of a fault to be diagnosed;
the system is used for respectively collecting stator currents of a motor which normally operates and different fault motors, carrying out Hilbert series transformation on the stator currents, carrying out Fourier decomposition on a transformation result, and extracting fault characteristic frequency components for constructing a model;
the fault characteristic frequency components used for building the model comprise frequency components of multiple fundamental wave frequencies of two times and multiple fundamental wave frequencies of three times corresponding to motor structure asymmetry caused by faults;
the training module uses the calibration data processed by the preprocessing module as a training sample for training a first-class support vector machine method, and stores a normal area of a mapping space for generating the first-class support vector machine method in the data storage module; using the test data processed by the preprocessing module as additional calibration data, and constructing a plurality of two classifiers by using a two-classification support vector machine method to generate new abnormal areas of a mapping space and store the new abnormal areas in a data storage module;
the data storage module is used for storing the normal area and the abnormal area of the mapping space of the training module;
the data acquisition module is used for acquiring the voltage of the storage battery of the external storage battery connected with the motor in a cold machine state or a heat machine state respectively if the fault alarm signal is monitored, wherein the heat machine state is a state after the generator is kept stand at a preset temperature for a preset time;
the fault diagnosis module is used for judging whether the voltage of the corresponding motor bottle is greater than the regulation protection voltage of the voltage regulator, and if so, determining that the voltage of the motor bottle is greater than the regulation protection voltage as a trigger factor of the fault alarm signal.
The support vector machine diagnosis module is used for inputting the characteristic frequency component of the fault to be diagnosed into an optimal support vector machine diagnosis model to diagnose the fault of the motor, evaluating the health degree of the motor, and outputting the fault category if the motor has the fault; the support vector machine diagnosis model building module is used for building an optimal support vector machine diagnosis model and setting the optimal support vector machine diagnosis model in the support vector machine diagnosis module;
the sample module is used for constructing a support vector machine diagnosis model sample based on the fault characteristic frequency component for constructing the model, and is used for carrying out time-frequency transformation on the time sequence signal of the motor to be tested to obtain an energy characteristic index of the time sequence signal as a real value sample of the motor to be tested;
the sample optimization module is used for optimizing core parameters in the support vector machine diagnosis model by adopting a grid search method or a genetic algorithm or a particle swarm algorithm to obtain an optimal support vector machine diagnosis model;
the diagnosis output module compares newly-increased data of motor operation with data of the data storage module, diagnoses by using a first-class support vector machine method and a plurality of second classifiers, is used for inputting real-value samples of quantum state description into a preset motor fault diagnosis model, and outputs the fault diagnosis result of the motor to be tested;
the quantum state description module is used for carrying out quantum state description on the real-value sample of the motor to be tested to obtain the real-value sample of the quantum state description.
2. The system and the method for intelligently diagnosing the fault of the servo motor according to claim 1 are characterized in that: the denoising processing method is singular value decomposition, and the time domain indexes are energy, kurtosis and mean square values.
3. The system and the method for intelligently diagnosing the faults of the servo motor according to claim 1, wherein the system comprises: the diagnosis output module diagnoses the motor as normal when the test data is included in the normal region, and diagnoses the motor as abnormal when the test data is not included in the normal region.
4. The system and the method for intelligently diagnosing the faults of the servo motor according to claim 1, wherein the system comprises: the support vector machine diagnosis model is a C-SVC model, and the kernel function is an RBF kernel function; the core parameter of the support vector machine diagnosis model is a penalty factor of the C-SVC model; the core parameter of the RBF kernel function is a weight factor of the kernel function.
5. The intelligent fault diagnosis method for the servo motor according to claim 1, characterized in that: the method comprises the following steps:
monitoring the fault alarm signal through a signal monitoring module, and judging whether the fault alarm signal is monitored;
if yes, respectively obtaining the voltage connected with the motor in a cold machine state or a heat machine state, wherein the heat machine state is a state after the motor is kept stand at a preset temperature for a preset time; judging whether the corresponding motor is larger than the regulating protection voltage of the voltage regulator, if so, determining that the motor is larger than the regulating protection voltage as a triggering factor of the fault alarm signal; if the fault alarm signal is not monitored and the motor is in the cold machine state or the hot machine state respectively, determining that the temperature is not an initiating factor of the fault alarm signal;
step two, acquiring a time sequence signal of the motor to be tested, calibrating, measuring a vibration signal of the motor to acquire calibration data while enabling the motor to operate in a specified operation mode by a data acquisition module, and transmitting the calibration data to a preprocessing module;
collecting stator current of a motor, performing Hilbert series transformation on the stator current, performing Fourier decomposition on a transformation result, and extracting a characteristic frequency component of a fault to be diagnosed;
performing time-frequency transformation on the time sequence signal of the motor to be tested to obtain an energy characteristic index of the time sequence signal, taking the energy characteristic index as a real-value sample of the motor to be tested, performing noise reduction processing on the acquired data by using a preprocessing module, performing time domain analysis on the noise-reduced signal to obtain a time domain index, and constructing a characteristic matrix;
inputting the characteristic frequency component of the fault to be diagnosed into an optimal support vector machine diagnosis model to diagnose the fault of the motor, evaluating the health degree of the motor, and outputting the fault category if the motor has the fault;
performing quantum state description on a real-value sample of the motor to be tested to obtain the real-value sample of the quantum state description, measuring a motor vibration signal to obtain test data while operating the motor in the specified operation mode again after the motor is operated, and performing signal processing on the test data by using the preprocessing procedure to construct a feature matrix;
inputting a real-value sample of the quantum state description into a preset motor fault diagnosis model, outputting a fault diagnosis result of a motor to be tested, generating a working procedure, and generating a normal region of a mapping space of a support vector machine method by using the calibration data as exercise data; using the test data as additional calibration data, and constructing a plurality of two classifiers by using a two-classification support vector machine method to generate a new abnormal region of a mapping space; storing the normal area and the abnormal area in a data storage module;
and seventhly, the diagnosis output module diagnoses the newly added data of the motor operation and the data of the data storage module, specifically, a first-class support vector machine method is used for distinguishing normal data and abnormal data, and a second-class support vector machine method is used for classifying the newly added abnormal data, wherein the first-class support vector machine method can predict the service life of the motor.
6. The intelligent fault diagnosis method for the servo motor according to claim 6, characterized in that: the time sequence signals of the motor to be tested comprise three-axis acceleration signals, current signals and voltage signals when the motor to be tested runs.
7. The intelligent fault diagnosis method for the servo motor according to claim 6, characterized in that: the process of performing time-frequency transformation on the time sequence signal of the motor to be tested to obtain the energy characteristic index of the time sequence signal specifically comprises the following steps:
and performing time-frequency transformation on the time sequence signal of the motor to be tested by adopting an improved empirical mode decomposition method to obtain an energy characteristic index of the time sequence signal.
8. The intelligent fault diagnosis method for the servo motor according to claim 6, characterized in that: the method for constructing the optimal support vector machine diagnosis model comprises the following steps:
respectively collecting stator currents of a motor which normally operates and different fault motors, carrying out Hilbert series transformation on the stator currents, carrying out Fourier decomposition on transformation results, and extracting fault characteristic frequency components for constructing a model;
the fault characteristic frequency components used for building the model comprise frequency components of multiple fundamental wave frequencies of two times and multiple fundamental wave frequencies of three times corresponding to motor structure asymmetry caused by faults;
constructing a support vector machine diagnosis model based on the fault characteristic frequency component for constructing the model; optimizing core parameters in the support vector machine diagnosis model by adopting a grid search method or a genetic algorithm or a particle swarm algorithm to obtain an optimal support vector machine diagnosis model;
the core parameters are parameters influencing the optimal objective function performance of the support vector machine diagnosis model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211535222.4A CN115877205A (en) | 2022-11-30 | 2022-11-30 | Intelligent fault diagnosis system and method for servo motor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211535222.4A CN115877205A (en) | 2022-11-30 | 2022-11-30 | Intelligent fault diagnosis system and method for servo motor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115877205A true CN115877205A (en) | 2023-03-31 |
Family
ID=85765468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211535222.4A Pending CN115877205A (en) | 2022-11-30 | 2022-11-30 | Intelligent fault diagnosis system and method for servo motor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115877205A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116150677A (en) * | 2023-04-19 | 2023-05-23 | 国家石油天然气管网集团有限公司 | Support vector machine-based oil transfer pump fault early warning method and system |
| CN116500441A (en) * | 2023-06-30 | 2023-07-28 | 无锡中基电机制造有限公司 | Motor fault detection and positioning method and system |
| CN116972914A (en) * | 2023-09-22 | 2023-10-31 | 华夏天信智能物联股份有限公司 | Intelligent testing method and system for frequency conversion integrated machine |
-
2022
- 2022-11-30 CN CN202211535222.4A patent/CN115877205A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116150677A (en) * | 2023-04-19 | 2023-05-23 | 国家石油天然气管网集团有限公司 | Support vector machine-based oil transfer pump fault early warning method and system |
| CN116500441A (en) * | 2023-06-30 | 2023-07-28 | 无锡中基电机制造有限公司 | Motor fault detection and positioning method and system |
| CN116500441B (en) * | 2023-06-30 | 2023-08-29 | 无锡中基电机制造有限公司 | Motor fault detection and positioning method and system |
| CN116972914A (en) * | 2023-09-22 | 2023-10-31 | 华夏天信智能物联股份有限公司 | Intelligent testing method and system for frequency conversion integrated machine |
| CN116972914B (en) * | 2023-09-22 | 2023-12-26 | 华夏天信智能物联股份有限公司 | Intelligent testing method and system for frequency conversion integrated machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115877205A (en) | Intelligent fault diagnosis system and method for servo motor | |
| CN103115789B (en) | Second generation small-wave support vector machine assessment method for damage and remaining life of metal structure | |
| CN111722145A (en) | Method for diagnosing slight fault of turn-to-turn short circuit of excitation winding of synchronous motor | |
| CN110763997A (en) | Early fault early warning method for synchronous motor stator | |
| CN113866642A (en) | Lithium ion battery fault diagnosis method based on gradient lifting tree | |
| CN112557966A (en) | Transformer winding looseness identification method based on local mean decomposition and support vector machine | |
| CN111209934A (en) | Fan fault prediction and alarm method and system | |
| CN111695452A (en) | Parallel reactor internal aging degree evaluation method based on RBF neural network | |
| CN110969185A (en) | Equipment abnormal state detection method based on data reconstruction | |
| CN115496108A (en) | Fault monitoring method and system based on manifold learning and big data analysis | |
| CN116956215A (en) | Fault diagnosis method and system for transmission system | |
| CN115758083A (en) | Motor bearing fault diagnosis method based on time domain and time-frequency domain fusion | |
| CN114325433A (en) | Lithium ion battery fault detection method and system based on electrochemical impedance spectrum test | |
| CN113627358A (en) | Multi-feature fusion turnout intelligent fault diagnosis method, system and equipment | |
| CN111474476B (en) | Motor fault prediction method | |
| CN113723496A (en) | Reactor iron core loosening fault diagnosis method, device and equipment | |
| Jianhui et al. | New fault diagnosis method for rolling bearing based on PCA | |
| Melendez et al. | Self-supervised Multi-stage Estimation of Remaining Useful Life for Electric Drive Units | |
| CN116578833A (en) | IGBT module aging fault diagnosis system based on optimized random forest model | |
| CN115238726A (en) | Rotating machinery state monitoring method based on performance degradation space fluctuation evaluation | |
| CN115169405A (en) | Hotel guest room equipment fault diagnosis method and system based on support vector machine | |
| Yun et al. | Fault diagnosis of wind turbine pitch system based on multiblock KPCA algorithm | |
| Deng et al. | A fractional hilbert transform order optimization algorithm based DE for bearing health monitoring | |
| Lorenz et al. | Vibration Data Analysis for Fault Detection in Manufacturing Systems-A Systematic Literature Review | |
| Zhao et al. | Fault Diagnosis of Rolling Bearings based on GA-SVM model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |