CN112287780A - Spectral kurtosis algorithm-based mechanical equipment fault diagnosis method and system and readable storage medium - Google Patents
Spectral kurtosis algorithm-based mechanical equipment fault diagnosis method and system and readable storage medium Download PDFInfo
- Publication number
- CN112287780A CN112287780A CN202011116315.4A CN202011116315A CN112287780A CN 112287780 A CN112287780 A CN 112287780A CN 202011116315 A CN202011116315 A CN 202011116315A CN 112287780 A CN112287780 A CN 112287780A
- Authority
- CN
- China
- Prior art keywords
- fault
- equipment
- signal
- spectral kurtosis
- vibration
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention relates to a method, a system and a readable storage medium for diagnosing faults of mechanical equipment based on a spectral kurtosis algorithm, wherein the method comprises the following steps: acquiring structural characteristics of mechanical equipment, and acquiring vibration signals of different measuring points of the mechanical equipment; preprocessing the vibration signal to obtain result information; extracting the characteristics of the result information, and acquiring the equipment fault characteristics by a resonance demodulation method to obtain fault information; and judging the fault type and the fault degree through the fault information to generate a maintenance sequence and a maintenance strategy.
Description
Technical Field
The invention relates to a mechanical equipment fault diagnosis method, in particular to a mechanical equipment fault diagnosis method and system based on a spectral kurtosis algorithm and a readable storage medium.
Background
With the improvement of comprehensive strength and continuous progress of technological level in China, the demand of modern industry on high-quality and low-cost products and safe production is higher and higher, the maintenance of industrial mechanical equipment is also quickly switched from preventive maintenance to real-time monitoring and intelligent fault diagnosis based on the state of the mechanical equipment, a rotary machine is one of the most widespread types in the mechanical equipment and has an irreplaceable status in industrial application, and the number of times of sudden shutdown of an operating unit can be effectively reduced based on the state monitoring and the fault maintenance of the rotary mechanical equipment, even accidents are avoided, so that the fault diagnosis of the rotary mechanical equipment has very important significance for ensuring the safe and efficient operation of the industrial equipment.
The existing mechanical equipment fault diagnosis only detects a simple vibration signal of mechanical equipment and evaluates the state of the mechanical equipment according to the vibration signal.
In order to be able to carry out accurate fault diagnosis on mechanical equipment, a system matched with the fault diagnosis system needs to be developed for control, fault characteristics are extracted through a resonance demodulation method, system resonance is excited through a broadband signal, low-frequency modulation information of resonance frequency is filtered, fault characteristic frequency bands are extracted, noise interference is overcome, vibration demodulation can be used for carrying out self-adaptive selection on required signal frequency bands, the precision of the equipment fault diagnosis process is improved, a fault diagnosis result is enabled to be closer to an actual value, how to realize accurate control on fault diagnosis of the mechanical equipment is a problem to be solved urgently.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a method, a system and a readable storage medium for diagnosing the fault of mechanical equipment based on a spectral kurtosis algorithm.
In order to achieve the purpose, the invention adopts the technical scheme that: a mechanical equipment fault diagnosis method based on a spectral kurtosis algorithm comprises the following steps:
acquiring structural characteristics of mechanical equipment, and acquiring vibration signals of different measuring points of the mechanical equipment;
preprocessing the vibration signal to obtain result information;
extracting the characteristics of the result information, and acquiring the equipment fault characteristics by a resonance demodulation method to obtain fault information;
and judging the fault type and the fault degree through the fault information to generate a maintenance sequence and a maintenance strategy.
In a preferred embodiment of the invention, the structural characteristics of mechanical equipment are acquired, and vibration signals of different measuring points of the mechanical equipment are acquired; the method specifically comprises the following steps:
establishing a multipoint measurement and multi-speed power spectrum entropy to monitor the vibration change rule of the equipment to obtain an equipment vibration signal;
decomposing the equipment vibration signal into a high resonance component signal and a low resonance component signal, and analyzing the waveform characteristics and the oscillation attributes of the high resonance component signal and the low resonance component signal respectively;
filtering the high resonance component signal and the low resonance component signal by a sparse resonance decomposition method;
and characterizing the real-time state data of the equipment according to an orthogonal matching tracking algorithm.
In a preferred embodiment of the invention, the fault characteristics of the equipment are obtained by a resonance demodulation method to obtain fault information; the method specifically comprises the following steps:
acquiring a vibration signal of equipment, selecting a resonance frequency center and a bandwidth of the vibration signal through a spectral kurtosis algorithm, and carrying out frequency band segmentation on the vibration signal;
extracting the periodic impact characteristics in the vibration signal,
calculating the spectral kurtosis of the vibration signal in the time domain signal through Fourier decomposition;
and identifying fault positions and fault types through spectral kurtosis information.
In a preferred embodiment of the present invention, the center of the resonance frequency and the bandwidth of the vibration signal are selected by a spectral kurtosis algorithm, specifically,
acquiring an equipment fault signal, and performing center frequency and bandwidth coefficient optimizing calculation on a fault parameter through a particle swarm algorithm;
judging whether the time domain kurtosis is larger than a preset threshold value or not;
if so, carrying out fault signal trap by using the current center frequency and bandwidth coefficient;
and performing resonance demodulation on the fault signal, and extracting fault characteristic frequency to obtain fault information.
In a preferred embodiment of the present invention, the particle swarm algorithm is specifically,
establishing a particle swarm fitness function, performing iterative computation on particles,
calculating a fitness function value corresponding to each iteration position;
setting iteration times, and determining an iteration initial position and an initial speed;
calculating a fitness function of the initial position particles, and updating a function extreme value according to a calculation result;
and repeating the iteration until the optimal adaptive value and the particle position are output.
In a preferred embodiment of the present invention, the particle swarm fitness function is expressed as
In the formula, M represents a fitness function, x represents a vibration signal, zeta represents a mean value of a discrete sequence of the vibration signal, and delta represents a standard deviation of the discrete sequence of the vibration signal; and lambda represents a fitness function correction coefficient.
The second aspect of the present invention also provides a system for diagnosing a fault of a mechanical device based on a spectral kurtosis algorithm, the system comprising: the fault diagnosis method program of the mechanical equipment based on the spectral kurtosis algorithm is executed by the processor to realize the following steps:
acquiring structural characteristics of mechanical equipment, and acquiring vibration signals of different measuring points of the mechanical equipment;
preprocessing the vibration signal to obtain result information;
extracting the characteristics of the result information, and acquiring the equipment fault characteristics by a resonance demodulation method to obtain fault information;
and judging the fault type and the fault degree through the fault information to generate a maintenance sequence and a maintenance strategy.
In a preferred embodiment of the invention, the structural characteristics of mechanical equipment are acquired, and vibration signals of different measuring points of the mechanical equipment are acquired; the method specifically comprises the following steps:
establishing a multipoint measurement and multi-speed power spectrum entropy to monitor the vibration change rule of the equipment to obtain an equipment vibration signal;
decomposing the equipment vibration signal into a high resonance component signal and a low resonance component signal, and analyzing the waveform characteristics and the oscillation attributes of the high resonance component signal and the low resonance component signal respectively;
filtering the high resonance component signal and the low resonance component signal by a sparse resonance decomposition method;
and characterizing the real-time state data of the equipment according to an orthogonal matching tracking algorithm.
In a preferred embodiment of the invention, the fault characteristics of the equipment are obtained by a resonance demodulation method to obtain fault information; the method specifically comprises the following steps:
acquiring a vibration signal of equipment, selecting a resonance frequency center and a bandwidth of the vibration signal through a spectral kurtosis algorithm, and carrying out frequency band segmentation on the vibration signal;
extracting the periodic impact characteristics in the vibration signal,
calculating the spectral kurtosis of the vibration signal in the time domain signal through Fourier decomposition;
and identifying fault positions and fault types through spectral kurtosis information.
A third aspect of the present invention provides a computer-readable storage medium, where a program of a method for diagnosing a fault of a mechanical device based on a spectral kurtosis algorithm is included in the computer-readable storage medium, and when the program of the method for diagnosing a fault of a mechanical device based on a spectral kurtosis algorithm is executed by a processor, the method for diagnosing a fault of a mechanical device based on a spectral kurtosis algorithm implements any one of the steps of the method for diagnosing a fault of a mechanical device based on a spectral kurtosis algorithm.
The invention solves the defects in the background technology, and has the following beneficial effects:
(1) the equipment signal is divided into a high-resonance component signal and a low-resonance component signal to be analyzed and demodulated separately, and a periodic oscillation signal in the mechanical equipment is excavated, so that the resonance frequency band of a fault signal is effectively identified, the fault signal is filtered, the noise of the environment where the mechanical equipment is located and the inherent noise of the mechanical equipment in the operation process are overcome, and a powerful basis is provided for the subsequent fault diagnosis of the mechanical equipment.
(2) The fault characteristics are extracted through a resonance demodulation method, system resonance is excited through a broadband signal, low-frequency modulation information of resonance frequency is filtered, a fault characteristic frequency band is extracted, noise interference is overcome, vibration demodulation can be used for selecting a required signal frequency band in a self-adaptive mode, the precision of the equipment fault diagnosis process is improved, and the fault diagnosis result is closer to an actual value.
(3) Harmonic components existing in the vibration signals are preprocessed through resonance demodulation, so that the kurtosis of a frequency domain statistical index envelope spectrum and the negative entropy of a square envelope spectrum tend to be maximized, an optimal filtering frequency band is further identified, weak fault characteristic information in the resonance frequency band can be identified, and fault diagnosis errors are reduced.
(4) Gaussian noise, harmonic waves and impact signals can be well inhibited through spectral kurtosis indexes, instantaneous change components of vibration signals can be monitored with a small signal-to-noise ratio, multiple fault coupling composite fault components in mechanical equipment are further identified, and fault positions are accurately located.
Drawings
The invention is further illustrated with reference to the following figures and examples.
FIG. 1 is a flow chart illustrating a method for diagnosing a fault of a mechanical device based on a spectral kurtosis algorithm according to the present invention;
FIG. 2 shows a flow chart of a method of obtaining a device vibration signal;
FIG. 3 shows a flow chart of a method for acquiring fault information by resonance demodulation;
FIG. 4 shows a flow diagram of a method for bandwidth selection by a spectral kurtosis algorithm;
FIG. 5 shows a particle swarm algorithm flow chart;
FIG. 6 shows a block diagram of a mechanical device fault diagnosis system based on a spectral kurtosis algorithm.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
FIG. 1 is a flow chart illustrating a method for diagnosing a fault of a mechanical device based on a spectral kurtosis algorithm according to the present invention.
As shown in fig. 1, a first aspect of the present invention provides a method for diagnosing a fault of a mechanical device based on a spectral kurtosis algorithm, including:
s102, acquiring structural characteristics of mechanical equipment, and acquiring vibration signals of different measuring points of the mechanical equipment;
s104, preprocessing the vibration signal to obtain result information;
s106, extracting the characteristics of the result information, and acquiring the equipment fault characteristics by a resonance demodulation method to obtain fault information;
and S108, judging the fault type and the fault degree according to the fault information, and generating a maintenance sequence and a maintenance strategy.
It should be noted that the fault characteristics are extracted by a resonance demodulation method, system resonance is excited by a broadband signal, low-frequency modulation information of resonance frequency is filtered, a fault characteristic frequency band is extracted, noise interference is overcome, vibration demodulation can select a required signal frequency band in a self-adaptive manner, the precision of the equipment fault diagnosis process is improved, a fault diagnosis result is closer to an actual value, harmonic components in the vibration signal are preprocessed by the resonance demodulation, the kurtosis of a frequency domain statistical index envelope spectrum and the negative entropy of a square envelope spectrum tend to be maximized, the optimal filtering frequency band is further identified, weak fault characteristic information in the resonance frequency band can be identified, and fault diagnosis errors are reduced.
As shown in FIG. 2, the present invention discloses a flow chart of a method for obtaining a vibration signal of a device;
according to the embodiment of the invention, the structural characteristics of mechanical equipment are obtained, and vibration signals of different measuring points of the mechanical equipment are collected; the method specifically comprises the following steps:
s202, establishing a multipoint measurement and multi-speed power spectrum entropy to monitor the vibration change rule of the equipment to obtain an equipment vibration signal;
s204, decomposing the equipment vibration signal into a high resonance component signal and a low resonance component signal, and analyzing the waveform characteristics and the oscillation attributes of the high resonance component signal and the low resonance component signal respectively;
s206, filtering the high resonance component signal and the low resonance component signal by a sparse resonance decomposition method;
and S208, representing the real-time state data of the equipment according to an orthogonal matching tracking algorithm.
It should be noted that, the device signal is divided into a high resonance component signal and a low resonance component signal to be analyzed and demodulated separately, a periodic oscillation signal in the mechanical device is excavated, so as to effectively identify the resonance frequency band of the fault signal, the fault signal is filtered, the noise of the environment where the mechanical device is located and the inherent noise in the operation process of the mechanical device are overcome, a powerful basis is provided for the subsequent fault diagnosis of the mechanical device, the signal is preprocessed by using a sparse resonance decomposition method, the periodic transient impact in the low resonance component is used as the continuous superposition of a series of shift pulses, the mechanical vibration signal is divided into a plurality of short-time sequence signals, the analysis result is stored in a database, the plurality of short-time sequence signals are subjected to iterative processing by a fault model, the redundancy of the database is effectively reduced, and the optimal iterative times are determined according to the noise level of the mechanical device itself, the method effectively improves the precision of fault diagnosis, avoids additional interference components, and realizes the rapidity and reliability of the diagnosis method.
The method comprises the steps of decomposing a vibration signal of the mechanical equipment into a high resonance component and a low resonance component with different oscillation attributes, filtering the high resonance component to obtain a filtering demodulation signal, carrying out multiple iterations on the filtering demodulation signal, and carrying out signal reconstruction to reduce interference impact and noise influence.
According to the embodiment of the invention, the expression of the equipment vibration signal is as follows:
in the formula: x represents a device vibration signal; λ represents a correction coefficient; m is the maximum order of the higher harmonic; f represents the vibration frequency of the equipment; a. themAn amplitude representing a vibration frequency of the mth order device;
an initial phase of the mth order device vibration frequency;
when the equipment is in a good running state, the vibration signal of the equipment is mainly composed of natural frequency components on a frequency spectrum, the higher harmonic frequency of the vibration signal is gradually reduced, and the amplitude of the vibration frequency of the equipment is lower;
when the equipment is in a fault condition, the natural frequency of the equipment is excited together with the vibration frequency, the vibration frequency component in the frequency is the main component, and the amplitude of the vibration frequency of the equipment has a high energy peak value.
As shown in fig. 3, the present invention discloses a flow chart of a method for acquiring fault information by resonance demodulation;
according to the embodiment of the invention, the fault characteristics of the equipment are obtained by a resonance demodulation method to obtain fault information; the method specifically comprises the following steps:
s302, acquiring a vibration signal of the equipment, selecting a resonance frequency center and a bandwidth of the vibration signal through a spectral kurtosis algorithm, and carrying out frequency band segmentation on the vibration signal;
s304, extracting periodic impact characteristics in the vibration signal,
s306, calculating the spectral kurtosis of the vibration signal in the time domain signal through Fourier decomposition;
and S308, identifying the fault position and the fault type through the spectral kurtosis information.
The fault types of the equipment comprise distributed faults and local faults, wherein the local faults mainly comprise cracks of a driving shaft of the equipment, abrasion of a shaft surface of the driving shaft and periodic collision impact caused in the process of meshing and contacting the driving shaft and a driven shaft; the distributed faults comprise misalignment of a driving shaft, eccentricity of the driving shaft and the like, Gaussian noise, harmonic waves and impact signals can be well inhibited through spectral kurtosis indexes, instantaneous change components of vibration signals can be monitored with a small signal-to-noise ratio, multiple fault coupled composite fault components in mechanical equipment are further identified, and fault positions are accurately positioned.
As shown in FIG. 4, the present invention discloses a flow chart of a bandwidth selection method by spectral kurtosis algorithm;
according to the embodiment of the invention, the resonance frequency center and the bandwidth of the vibration signal are selected through a spectral kurtosis algorithm, specifically,
s402, acquiring an equipment fault signal, and performing center frequency and bandwidth coefficient optimizing calculation on a fault parameter through a particle swarm algorithm;
s404, judging whether the time domain kurtosis is larger than a preset threshold value or not;
s406, if the central frequency and the bandwidth coefficient are larger than the preset central frequency and the bandwidth coefficient, carrying out fault signal trap;
and S408, performing resonance demodulation on the fault signal, and extracting fault characteristic frequency to obtain fault information.
It should be noted that the notch is a narrow-band filter, which can filter out specific harmonic interference signals and pass other signals at the same time, and the narrow-band-stop characteristic of the notch can retain signals in the vibration signal except for specific harmonics, and the notch parameters only depend on the power frequency rotation speed information and the structural parameters of the rotating equipment.
The fault signal notch utilizes the narrow-band filtering characteristic of the notch to filter out specific harmonic interference components,
setting the frequency of a specific harmonic component to be filtered to x0The filter is set as x0At position point y, x ═ x0The amplitude characteristic of the filter is 0 and x is equal to the deviation x0The amplitude characteristic is constant, and the characteristic transfer function of the filter is expressed as follows:
where Z represents the characteristic transfer function, a represents the filter gain coefficient, and y represents the location point.
As shown in FIG. 5, the present invention discloses a particle swarm algorithm flowchart;
according to the embodiment of the invention, the particle swarm algorithm is specifically,
s502, establishing a particle swarm fitness function, performing iterative computation on particles,
s504, calculating a fitness function value corresponding to each iteration position;
s506, setting iteration times, and determining an iteration initial position and an initial speed;
s508, calculating a fitness function of the initial position particles, and updating a function extreme value according to a calculation result;
and S510, repeating iteration until the optimal adaptive value and the particle position are output.
According to the embodiment of the invention, the particle swarm fitness function expression is
In the formula, M represents a fitness function, x represents a vibration signal, zeta represents a mean value of a discrete sequence of the vibration signal, and delta represents a standard deviation of the discrete sequence of the vibration signal; and lambda represents a fitness function correction coefficient.
As shown in FIG. 6, the invention discloses a system block diagram for diagnosing faults of mechanical equipment based on a spectral kurtosis algorithm.
The second aspect of the present invention also provides a system for diagnosing a fault of a mechanical device based on a spectral kurtosis algorithm, where the system 6 includes: the system comprises a memory 61 and a processor 62, wherein the memory comprises a program of a mechanical equipment fault diagnosis method based on a spectral kurtosis algorithm, and the program of the mechanical equipment fault diagnosis method based on the spectral kurtosis algorithm realizes the following steps when being executed by the processor:
acquiring structural characteristics of mechanical equipment, and acquiring vibration signals of different measuring points of the mechanical equipment;
preprocessing the vibration signal to obtain result information;
extracting the characteristics of the result information, and acquiring the equipment fault characteristics by a resonance demodulation method to obtain fault information;
and judging the fault type and the fault degree through the fault information to generate a maintenance sequence and a maintenance strategy.
It should be noted that the fault characteristics are extracted by a resonance demodulation method, system resonance is excited by a broadband signal, low-frequency modulation information of resonance frequency is filtered, a fault characteristic frequency band is extracted, noise interference is overcome, vibration demodulation can select a required signal frequency band in a self-adaptive manner, the precision of the equipment fault diagnosis process is improved, a fault diagnosis result is closer to an actual value, harmonic components in the vibration signal are preprocessed by the resonance demodulation, the kurtosis of a frequency domain statistical index envelope spectrum and the negative entropy of a square envelope spectrum tend to be maximized, the optimal filtering frequency band is further identified, weak fault characteristic information in the resonance frequency band can be identified, and fault diagnosis errors are reduced.
According to the embodiment of the invention, the structural characteristics of mechanical equipment are obtained, and vibration signals of different measuring points of the mechanical equipment are collected; the method specifically comprises the following steps:
establishing a multipoint measurement and multi-speed power spectrum entropy to monitor the vibration change rule of the equipment to obtain an equipment vibration signal;
decomposing the equipment vibration signal into a high resonance component signal and a low resonance component signal, and analyzing the waveform characteristics and the oscillation attributes of the high resonance component signal and the low resonance component signal respectively;
filtering the high resonance component signal and the low resonance component signal by a sparse resonance decomposition method;
and characterizing the real-time state data of the equipment according to an orthogonal matching tracking algorithm.
It should be noted that, the device signal is divided into a high resonance component signal and a low resonance component signal to be analyzed and demodulated separately, a periodic oscillation signal in the mechanical device is excavated, so as to effectively identify the resonance frequency band of the fault signal, the fault signal is filtered, the noise of the environment where the mechanical device is located and the inherent noise in the operation process of the mechanical device are overcome, a powerful basis is provided for the subsequent fault diagnosis of the mechanical device, the signal is preprocessed by using a sparse resonance decomposition method, the periodic transient impact in the low resonance component is used as the continuous superposition of a series of shift pulses, the mechanical vibration signal is divided into a plurality of short-time sequence signals, the analysis result is stored in a database, the plurality of short-time sequence signals are subjected to iterative processing by a fault model, the redundancy of the database is effectively reduced, and the optimal iterative times are determined according to the noise level of the mechanical device itself, the method effectively improves the precision of fault diagnosis, avoids additional interference components, and realizes the rapidity and reliability of the diagnosis method.
The method comprises the steps of decomposing a vibration signal of the mechanical equipment into a high resonance component and a low resonance component with different oscillation attributes, filtering the high resonance component to obtain a filtering demodulation signal, carrying out multiple iterations on the filtering demodulation signal, and carrying out signal reconstruction to reduce interference impact and noise influence.
According to the embodiment of the invention, the expression of the equipment vibration signal is as follows:
in the formula: x represents a device vibration signal; λ represents a correction coefficient; m is the maximum order of the higher harmonic; f represents the vibration frequency of the equipment; a. themAn amplitude representing a vibration frequency of the mth order device;
an initial phase of the mth order device vibration frequency;
when the equipment is in a good running state, the vibration signal of the equipment is mainly composed of natural frequency components on a frequency spectrum, the higher harmonic frequency of the vibration signal is gradually reduced, and the amplitude of the vibration frequency of the equipment is lower;
when the equipment is in a fault condition, the natural frequency of the equipment is excited together with the vibration frequency, the vibration frequency component in the frequency is the main component, and the amplitude of the vibration frequency of the equipment has a high energy peak value.
According to the embodiment of the invention, the fault characteristics of the equipment are obtained by a resonance demodulation method to obtain fault information; the method specifically comprises the following steps:
acquiring a vibration signal of equipment, selecting a resonance frequency center and a bandwidth of the vibration signal through a spectral kurtosis algorithm, and carrying out frequency band segmentation on the vibration signal;
extracting the periodic impact characteristics in the vibration signal,
calculating the spectral kurtosis of the vibration signal in the time domain signal through Fourier decomposition;
and identifying fault positions and fault types through spectral kurtosis information.
The fault types of the equipment comprise distributed faults and local faults, wherein the local faults mainly comprise cracks of a driving shaft of the equipment, abrasion of a shaft surface of the driving shaft and periodic collision impact caused in the process of meshing and contacting the driving shaft and a driven shaft; the distributed faults comprise misalignment of a driving shaft, eccentricity of the driving shaft and the like, Gaussian noise, harmonic waves and impact signals can be well inhibited through spectral kurtosis indexes, instantaneous change components of vibration signals can be monitored with a small signal-to-noise ratio, multiple fault coupled composite fault components in mechanical equipment are further identified, and fault positions are accurately positioned.
According to the embodiment of the invention, the resonance frequency center and the bandwidth of the vibration signal are selected through a spectral kurtosis algorithm, specifically,
acquiring an equipment fault signal, and performing center frequency and bandwidth coefficient optimizing calculation on a fault parameter through a particle swarm algorithm;
judging whether the time domain kurtosis is larger than a preset threshold value or not;
if so, carrying out fault signal trap by using the current center frequency and bandwidth coefficient;
and performing resonance demodulation on the fault signal, and extracting fault characteristic frequency to obtain fault information.
It should be noted that the notch is a narrow-band filter, which can filter out specific harmonic interference signals and pass other signals at the same time, and the narrow-band-stop characteristic of the notch can retain signals in the vibration signal except for specific harmonics, and the notch parameters only depend on the power frequency rotation speed information and the structural parameters of the rotating equipment.
The fault signal notch utilizes the narrow-band filtering characteristic of the notch to filter out specific harmonic interference components,
setting the frequency of a specific harmonic component to be filtered to x0The filter is set as x0At position point y, x ═ x0The amplitude characteristic of the filter is 0 and x is equal to the deviation x0The amplitude characteristic is constant, and the characteristic transfer function of the filter is expressed as follows:
where Z represents the characteristic transfer function, a represents the filter gain coefficient, and y represents the location point.
According to the embodiment of the invention, the particle swarm algorithm is specifically,
establishing a particle swarm fitness function, performing iterative computation on particles,
calculating a fitness function value corresponding to each iteration position;
setting iteration times, and determining an iteration initial position and an initial speed;
calculating a fitness function of the initial position particles, and updating a function extreme value according to a calculation result;
and repeating the iteration until the optimal adaptive value and the particle position are output.
According to the embodiment of the invention, the particle swarm fitness function expression is
In the formula, M represents a fitness function, x represents a vibration signal, zeta represents a mean value of a discrete sequence of the vibration signal, and delta represents a standard deviation of the discrete sequence of the vibration signal; and lambda represents a fitness function correction coefficient.
A third aspect of the present invention provides a computer-readable storage medium, where a program of a method for diagnosing a fault of a mechanical device based on a spectral kurtosis algorithm is included in the computer-readable storage medium, and when the program of the method for diagnosing a fault of a mechanical device based on a spectral kurtosis algorithm is executed by a processor, the method for diagnosing a fault of a mechanical device based on a spectral kurtosis algorithm implements any one of the steps of the method for diagnosing a fault of a mechanical device based on a spectral kurtosis algorithm.
The equipment signal is divided into a high-resonance component signal and a low-resonance component signal to be analyzed and demodulated separately, and a periodic oscillation signal in the mechanical equipment is excavated, so that the resonance frequency band of a fault signal is effectively identified, the fault signal is filtered, the noise of the environment where the mechanical equipment is located and the inherent noise of the mechanical equipment in the operation process are overcome, and a powerful basis is provided for the subsequent fault diagnosis of the mechanical equipment.
The fault characteristics are extracted through a resonance demodulation method, system resonance is excited through a broadband signal, low-frequency modulation information of resonance frequency is filtered, a fault characteristic frequency band is extracted, noise interference is overcome, vibration demodulation can be used for selecting a required signal frequency band in a self-adaptive mode, the precision of the equipment fault diagnosis process is improved, and the fault diagnosis result is closer to an actual value.
Harmonic components existing in the vibration signals are preprocessed through resonance demodulation, so that the kurtosis of a frequency domain statistical index envelope spectrum and the negative entropy of a square envelope spectrum tend to be maximized, an optimal filtering frequency band is further identified, weak fault characteristic information in the resonance frequency band can be identified, and fault diagnosis errors are reduced.
Gaussian noise, harmonic waves and impact signals can be well inhibited through spectral kurtosis indexes, instantaneous change components of vibration signals can be monitored with a small signal-to-noise ratio, multiple fault coupling composite fault components in mechanical equipment are further identified, and fault positions are accurately located.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of a unit is only one logical function division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A mechanical equipment fault diagnosis method based on a spectral kurtosis algorithm is characterized by comprising the following steps:
acquiring structural characteristics of mechanical equipment, and acquiring vibration signals of different measuring points of the mechanical equipment;
preprocessing the vibration signal to obtain result information;
extracting the characteristics of the result information, and acquiring the equipment fault characteristics by a resonance demodulation method to obtain fault information;
and judging the fault type and the fault degree through the fault information to generate a maintenance sequence and a maintenance strategy.
2. The method for diagnosing the fault of the mechanical equipment based on the spectral kurtosis algorithm as claimed in claim 1, wherein: acquiring structural characteristics of mechanical equipment, and acquiring vibration signals of different measuring points of the mechanical equipment; the method specifically comprises the following steps:
establishing a multipoint measurement and multi-speed power spectrum entropy to monitor the vibration change rule of the equipment to obtain an equipment vibration signal;
decomposing the equipment vibration signal into a high resonance component signal and a low resonance component signal, and analyzing the waveform characteristics and the oscillation attributes of the high resonance component signal and the low resonance component signal respectively;
filtering the high resonance component signal and the low resonance component signal by a sparse resonance decomposition method;
and characterizing the real-time state data of the equipment according to an orthogonal matching tracking algorithm.
3. The method for diagnosing the fault of the mechanical equipment based on the spectral kurtosis algorithm as claimed in claim 1, wherein: acquiring equipment fault characteristics by a resonance demodulation method to obtain fault information; the method specifically comprises the following steps:
acquiring a vibration signal of equipment, selecting a resonance frequency center and a bandwidth of the vibration signal through a spectral kurtosis algorithm, and carrying out frequency band segmentation on the vibration signal;
extracting the periodic impact characteristics in the vibration signal,
calculating the spectral kurtosis of the vibration signal in the time domain signal through Fourier decomposition;
and identifying fault positions and fault types through spectral kurtosis information.
4. The method for diagnosing the fault of the mechanical equipment based on the spectral kurtosis algorithm as claimed in claim 3, wherein: the resonance frequency center and the bandwidth of the vibration signal are selected by a spectral kurtosis algorithm, specifically,
acquiring an equipment fault signal, and performing center frequency and bandwidth coefficient optimizing calculation on a fault parameter through a particle swarm algorithm;
judging whether the time domain kurtosis is larger than a preset threshold value or not;
if so, carrying out fault signal trap by using the current center frequency and bandwidth coefficient;
and performing resonance demodulation on the fault signal, and extracting fault characteristic frequency to obtain fault information.
5. The method of claim 4, wherein the method comprises a step of performing a spectral kurtosis algorithm based on a spectral kurtosis algorithm, wherein the spectral kurtosis algorithm comprises a step of: the particle swarm optimization is specifically that,
establishing a particle swarm fitness function, performing iterative computation on particles,
calculating a fitness function value corresponding to each iteration position;
setting iteration times, and determining an iteration initial position and an initial speed;
calculating a fitness function of the initial position particles, and updating a function extreme value according to a calculation result;
and repeating the iteration until the optimal adaptive value and the particle position are output.
6. The method of claim 5, wherein the method comprises:
the particle swarm fitness function expression is
In the formula, M represents a fitness function, x represents a vibration signal, zeta represents a mean value of a discrete sequence of the vibration signal, and delta represents a standard deviation of the discrete sequence of the vibration signal; and lambda represents a fitness function correction coefficient.
7. A mechanical equipment fault diagnosis system based on a spectral kurtosis algorithm is characterized by comprising: the fault diagnosis method program of the mechanical equipment based on the spectral kurtosis algorithm is executed by the processor to realize the following steps:
acquiring structural characteristics of mechanical equipment, and acquiring vibration signals of different measuring points of the mechanical equipment;
preprocessing the vibration signal to obtain result information;
extracting the characteristics of the result information, and acquiring the equipment fault characteristics by a resonance demodulation method to obtain fault information;
and judging the fault type and the fault degree through the fault information to generate a maintenance sequence and a maintenance strategy.
8. The system of claim 7, wherein the system comprises a spectral kurtosis algorithm based on a set of spectral kurtosis algorithms, and wherein the spectral kurtosis algorithm comprises:
acquiring structural characteristics of mechanical equipment, and acquiring vibration signals of different measuring points of the mechanical equipment; the method specifically comprises the following steps:
establishing a multipoint measurement and multi-speed power spectrum entropy to monitor the vibration change rule of the equipment to obtain an equipment vibration signal;
decomposing the equipment vibration signal into a high resonance component signal and a low resonance component signal, and analyzing the waveform characteristics and the oscillation attributes of the high resonance component signal and the low resonance component signal respectively;
filtering the high resonance component signal and the low resonance component signal by a sparse resonance decomposition method;
and characterizing the real-time state data of the equipment according to an orthogonal matching tracking algorithm.
9. The system of claim 7, wherein the system comprises a spectral kurtosis algorithm based on a set of spectral kurtosis algorithms, and wherein the spectral kurtosis algorithm comprises:
acquiring equipment fault characteristics by a resonance demodulation method to obtain fault information; the method specifically comprises the following steps:
acquiring a vibration signal of equipment, selecting a resonance frequency center and a bandwidth of the vibration signal through a spectral kurtosis algorithm, and carrying out frequency band segmentation on the vibration signal;
extracting the periodic impact characteristics in the vibration signal,
calculating the spectral kurtosis of the vibration signal in the time domain signal through Fourier decomposition;
and identifying fault positions and fault types through spectral kurtosis information.
10. A computer-readable storage medium characterized by: the computer readable storage medium includes therein a spectral kurtosis algorithm based mechanical device fault diagnosis method program, which when executed by a processor, implements the steps of the spectral kurtosis algorithm based mechanical device fault diagnosis method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011116315.4A CN112287780A (en) | 2020-10-19 | 2020-10-19 | Spectral kurtosis algorithm-based mechanical equipment fault diagnosis method and system and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011116315.4A CN112287780A (en) | 2020-10-19 | 2020-10-19 | Spectral kurtosis algorithm-based mechanical equipment fault diagnosis method and system and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112287780A true CN112287780A (en) | 2021-01-29 |
Family
ID=74496343
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011116315.4A Withdrawn CN112287780A (en) | 2020-10-19 | 2020-10-19 | Spectral kurtosis algorithm-based mechanical equipment fault diagnosis method and system and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112287780A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114166507A (en) * | 2021-11-19 | 2022-03-11 | 郑州恩普特科技股份有限公司 | Harmonic recognition method based on rapid spectral kurtosis |
| CN114674552A (en) * | 2022-03-21 | 2022-06-28 | 烟台杰瑞石油装备技术有限公司 | Fault judging method for gear box |
| CN114706904A (en) * | 2022-03-24 | 2022-07-05 | 四川华能泸定水电有限公司 | Control method, equipment and medium based on vibroflotation construction big data optimization strategy |
| CN114882912A (en) * | 2022-07-08 | 2022-08-09 | 杭州兆华电子股份有限公司 | Method and device for testing transient defects of time domain of acoustic signal |
| CN116578856A (en) * | 2023-05-16 | 2023-08-11 | 利维智能（深圳）有限公司 | Fault detection method, device, computer equipment and storage medium |
-
2020
- 2020-10-19 CN CN202011116315.4A patent/CN112287780A/en not_active Withdrawn
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114166507A (en) * | 2021-11-19 | 2022-03-11 | 郑州恩普特科技股份有限公司 | Harmonic recognition method based on rapid spectral kurtosis |
| CN114166507B (en) * | 2021-11-19 | 2024-04-12 | 郑州恩普特科技股份有限公司 | Harmonic identification method based on rapid spectral kurtosis |
| CN114674552A (en) * | 2022-03-21 | 2022-06-28 | 烟台杰瑞石油装备技术有限公司 | Fault judging method for gear box |
| CN114674552B (en) * | 2022-03-21 | 2023-11-24 | 烟台杰瑞石油装备技术有限公司 | Fault discrimination method for gear box |
| CN114706904A (en) * | 2022-03-24 | 2022-07-05 | 四川华能泸定水电有限公司 | Control method, equipment and medium based on vibroflotation construction big data optimization strategy |
| CN114882912A (en) * | 2022-07-08 | 2022-08-09 | 杭州兆华电子股份有限公司 | Method and device for testing transient defects of time domain of acoustic signal |
| CN114882912B (en) * | 2022-07-08 | 2022-09-23 | 杭州兆华电子股份有限公司 | Method and device for testing transient defects of time domain of acoustic signal |
| CN116578856A (en) * | 2023-05-16 | 2023-08-11 | 利维智能（深圳）有限公司 | Fault detection method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112287780A (en) | Spectral kurtosis algorithm-based mechanical equipment fault diagnosis method and system and readable storage medium | |
| Lee et al. | Application of deep neural network and generative adversarial network to industrial maintenance: A case study of induction motor fault detection | |
| Wu et al. | Induction machine fault detection using SOM-based RBF neural networks | |
| GB2616970A (en) | Gearbox fault diagnosis model training method and gearbox fault diagnosis method | |
| CN115688018B (en) | Method for monitoring state and diagnosing faults of bearing under multiple working conditions | |
| CN107884190A (en) | The Method for Bearing Fault Diagnosis decomposed based on variation mode decomposition and wavelet singular | |
| CN106198013B (en) | A kind of envelope Analysis Method based on empirical mode decomposition filtering | |
| CN112834224B (en) | Nuclear power steam turbine generator health state assessment method and system | |
| CN106153339B (en) | A kind of envelope Analysis Method based on the filtering of variation Mode Decomposition | |
| CN111504385A (en) | Multi-parameter monitoring device and method suitable for abnormal state of mechanical equipment | |
| CN112199888A (en) | Rotary equipment fault diagnosis method and system based on deep residual error network and readable storage medium | |
| CN106096200B (en) | A kind of envelope Analysis Method based on wavelet decomposition and spectrum kurtosis | |
| Jaber et al. | A simulation of non-stationary signal analysis using wavelet transform based on LabVIEW and Matlab | |
| CN111881594A (en) | Non-stationary signal state monitoring method and system for nuclear power equipment | |
| CN105954031B (en) | A kind of envelope Analysis Method based on unusual spectral factorization filtering | |
| CN112200060A (en) | Network model-based rotating equipment fault diagnosis method and system and readable storage medium | |
| CN106153333B (en) | A kind of envelope Analysis Method based on wavelet decomposition filtering | |
| CN116298868A (en) | Method for detecting static eccentric faults of wound-rotor brushless double-fed motor | |
| CN115310497A (en) | Abnormity identification method for bearing of numerical control machine tool | |
| CN112688836B (en) | Energy routing equipment online dynamic sensing method based on deep self-coding network | |
| Amer et al. | Machine tool condition monitoring using sweeping filter techniques | |
| CN115409367A (en) | Intelligent power grid health state assessment method and system based on Internet of things | |
| CN115221914A (en) | Rotating machinery fault diagnosis method based on enhanced octyl geometric modal decomposition | |
| CN114415018A (en) | Self-learning grating interference spectrum analysis technology for motor fault early warning | |
| CN112182490B (en) | Reactor state diagnosis method and system |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210129 |
|
| WW01 | Invention patent application withdrawn after publication |