CN116304649A - Motor fault signal feature extraction method, system, computer and storage medium - Google Patents
Motor fault signal feature extraction method, system, computer and storage medium Download PDFInfo
- Publication number
- CN116304649A CN116304649A CN202310582559.9A CN202310582559A CN116304649A CN 116304649 A CN116304649 A CN 116304649A CN 202310582559 A CN202310582559 A CN 202310582559A CN 116304649 A CN116304649 A CN 116304649A
- Authority
- CN
- China
- Prior art keywords
- particle
- algorithm
- rssd
- signal
- optimal
- 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- Withdrawn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
- 238000000605 extraction Methods 0.000 title claims abstract description 42
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 142
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 12
- 239000002245 particle Substances 0.000 claims description 154
- 230000000875 corresponding effect Effects 0.000 claims description 109
- 230000006870 function Effects 0.000 claims description 76
- 238000000354 decomposition reaction Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000002596 correlated effect Effects 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 description 22
- 238000005457 optimization Methods 0.000 description 12
- 230000009286 beneficial effect Effects 0.000 description 7
- 230000013016 learning Effects 0.000 description 5
- 238000013459 approach Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009326 social learning Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/34—Testing dynamo-electric machines
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Control Of Electric Motors In General (AREA)
Abstract
The invention provides a motor fault signal feature extraction method, a system, a computer and a storage medium, wherein the method comprises the following steps: when a fault signal is detected, initializing parameters in an RSSD algorithm and a PF-PSO algorithm at the same time, and calculating an optimal parameter matched with the RSSD algorithm through the PF-PSO algorithm based on a preset rule, wherein the optimal parameter has uniqueness; inputting the optimal parameters into the RSSD algorithm so that the RSSD algorithm outputs a corresponding optimal low-resonance component signal; and performing fault characteristic identification processing on the optimal low-resonance component signal so as to correspondingly extract fault characteristic information corresponding to the fault signal. By the method, the penalty function concept in the PF-PSO algorithm can be introduced into the RSSD algorithm, so that the optimized RSSD algorithm has high convergence rate and high adaptability.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, a system, a computer, and a storage medium for extracting a motor fault signal feature.
Background
As in the prior art, the motor transmission is an indispensable component in industrial equipment, and therefore, whether the motor transmission can operate normally has an important influence on the stability of the industrial equipment.
The motor bearing is one of important components in the motor transmission device, and in the existing rotary mechanical equipment, the frequency of the motor bearing faults is high, meanwhile, the motor bearing is used as a key component in a motor unit, when the motor bearing faults and is not found in time, abnormal sound and vibration of unit facilities are easily caused, the whole equipment is damaged when serious, and unnecessary loss is brought to factories.
In addition, the impact information caused by the existing motor transmission faults is weak, and meanwhile, the fault characteristics of the motor transmission often show nonlinear and non-stable characteristic information under the environments of high rotating speed, strong load and strong noise of the motor.
Therefore, in order to overcome the shortcomings of the prior art, it is necessary to provide a method capable of extracting the characteristics of the motor transmission fault signal under the complex working condition so as to analyze the cause of the motor transmission fault.
Disclosure of Invention
Based on the above, the invention aims to provide a motor fault signal feature extraction method, a system, a computer and a storage medium, so as to provide a method capable of extracting motor transmission fault signal features under complex working conditions.
An embodiment of the present invention provides a method for extracting a motor fault signal feature, where the method includes:
when a fault signal is detected, initializing parameters in an RSSD algorithm and a PF-PSO algorithm at the same time, and calculating optimal parameters matched with the RSSD algorithm through the PF-PSO algorithm based on a preset rule, wherein the optimal parameters have uniqueness;
inputting the optimal parameters into the RSSD algorithm so that the RSSD algorithm outputs a corresponding optimal low-resonance component signal;
and carrying out fault characteristic identification processing on the optimal low-resonance component signal so as to correspondingly extract fault characteristic information corresponding to the fault signal.
The beneficial effects of the invention are as follows: when a fault signal is detected, initializing parameters in an RSSD algorithm and a PF-PSO algorithm at the same time, and calculating an optimal parameter matched with the RSSD algorithm through the PF-PSO algorithm based on a preset rule, wherein the optimal parameter has uniqueness; further, inputting the optimal parameters into an RSSD algorithm so that the RSSD algorithm outputs a corresponding optimal low-resonance component signal; and finally, performing fault characteristic identification processing on the optimal low-resonance component signal to correspondingly extract fault characteristic information corresponding to the fault signal. By the method, the penalty function idea in the PF-PSO algorithm can be introduced into the RSSD algorithm, so that the optimized RSSD algorithm has higher convergence speed and better adaptability, required fault characteristic information can be simply and rapidly extracted from fault signals, and the method is beneficial to the wide-range use of motor transmission devices.
Preferably, the step of calculating the optimal parameter adapted to the RSSD algorithm by the PF-PSO algorithm based on a preset rule includes:
detecting a plurality of penalty function particle populations contained in the PF-PSO algorithm, and decomposing the penalty function particle populations through the RSSD algorithm to generate a plurality of corresponding particle individuals;
iteratively updating the particle positions of a plurality of particle individuals based on a low resonance component signal CK minimum principle, and judging whether the particle positions corresponding to the updated particle individuals meet preset constraint conditions or not in real time;
and if the particle positions corresponding to the updated particle individuals meet the constraint conditions, judging that the particle positions corresponding to the current particle individuals are the optimal parameters.
Preferably, the step of simultaneously initializing parameters in the RSSD algorithm and the PF-PSO algorithm when the fault signal is detected includes:
when the fault signal is detected, initializing penalty function particle population parameters in the PF-PSO algorithm, and randomly generating a plurality of penalty function particle populations;
and selecting quality factors corresponding to the penalty function particle populations, and setting optimizing intervals corresponding to the quality factors, wherein the optimizing intervals have uniqueness.
Preferably, the low resonance component signal CK-based minimization principle includes:
selecting a correlation coefficient C and a kurtosis factor K which are matched with the PF-PSO, and establishing a mapping relation between the correlation coefficient C and the kurtosis factor K;
performing fusion operation on the correlation coefficient C and the kurtosis factor K to generate a corresponding low-resonance component signal CK, and setting the low-resonance component signal CK as an adaptability function of the PF-PSO algorithm;
wherein, the expression of the kurtosis factor is:
wherein μ represents the mean value of the signal, σ represents the standard deviation, E represents the expected value, and the correlation coefficient C has the following expression:
wherein x is i And y i Respectively representing the value of the current signal x, y at the i-th point,
and->
Respectively represent the average value of the current signals x and y, and the correlation coefficient C E [0,1 ]]When the correlation coefficient c=0, it indicates that the signal x is completely uncorrelated with the signal y, and when the correlation coefficient c=1, it indicates that the signal x is completely correlated with the signal y, and n indicates a constant, and the low resonance component signal CK is defined as:
CK=C/K
when the correlation coefficient reaches the minimum value, the low resonance component signal reaches the minimum value at the same time, and the decomposition effect of the RSSD algorithm reaches the optimal value.
Preferably, the step of iteratively updating the particle positions of a plurality of individual particles based on the low resonance component signal CK minima principle includes:
calculating the fitness value corresponding to each particle individual through the fitness function, and comparing the fitness value corresponding to each particle individual with the individual extremum and the global extremum corresponding to each particle individual to obtain a corresponding comparison result;
based on the comparison result, searching corresponding local individuals and globally optimal individuals in a plurality of particle individuals through the PF-PSO algorithm;
updating the inertia weight value of the global optimal individual, and determining the particle position and the particle speed corresponding to the global optimal individual according to the inertia weight value.
A second aspect of the embodiment of the present invention provides a system for extracting a fault signal feature of a motor, where the system includes:
the calculation module is used for initializing parameters in an RSSD algorithm and a PF-PSO algorithm at the same time when a fault signal is detected, and calculating optimal parameters matched with the RSSD algorithm through the PF-PSO algorithm based on a preset rule, wherein the optimal parameters have uniqueness;
The output module is used for inputting the optimal parameters into the RSSD algorithm so that the RSSD algorithm outputs a corresponding optimal low-resonance component signal;
and the extraction module is used for carrying out fault characteristic identification processing on the optimal low-resonance component signal so as to correspondingly extract fault characteristic information corresponding to the fault signal.
In the above motor fault signal feature extraction system, the calculation module is specifically configured to:
detecting a plurality of penalty function particle populations contained in the PF-PSO algorithm, and decomposing the penalty function particle populations through the RSSD algorithm to generate a plurality of corresponding particle individuals;
iteratively updating the particle positions of a plurality of particle individuals based on a low resonance component signal CK minimum principle, and judging whether the particle positions corresponding to the updated particle individuals meet preset constraint conditions or not in real time;
and if the particle positions corresponding to the updated particle individuals meet the constraint conditions, judging that the particle positions corresponding to the current particle individuals are the optimal parameters.
In the above motor fault signal feature extraction system, the calculation module is further specifically configured to:
When the fault signal is detected, initializing penalty function particle population parameters in the PF-PSO algorithm, and randomly generating a plurality of penalty function particle populations;
and selecting quality factors corresponding to the penalty function particle populations, and setting optimizing intervals corresponding to the quality factors, wherein the optimizing intervals have uniqueness.
In the above motor fault signal feature extraction system, the low resonance component signal CK-based minima principle includes:
selecting a correlation coefficient C and a kurtosis factor K which are matched with the PF-PSO, and establishing a mapping relation between the correlation coefficient C and the kurtosis factor K;
performing fusion operation on the correlation coefficient C and the kurtosis factor K to generate a corresponding low-resonance component signal CK, and setting the low-resonance component signal CK as an adaptability function of the PF-PSO algorithm;
wherein, the expression of the kurtosis factor is:
wherein μ represents the mean value of the signal, σ represents the standard deviation, E represents the expected value, and the correlation coefficient C has the following expression:
wherein x is i And y i Respectively representing the value of the current signal x, y at the i-th point,
and->
Respectively represent the average value of the current signals x and y, and the correlation coefficient C E [0,1 ] ]When the correlation coefficient c=0, it indicates that the signal x is completely uncorrelated with the signal y, and when the correlation coefficient c=1, it indicates that the signal x is completely correlated with the signal y, and n indicates a constant, and the low resonance component signal CK is defined as:
CK=C/K
when the correlation coefficient reaches the minimum value, the low resonance component signal reaches the minimum value at the same time, and the decomposition effect of the RSSD algorithm reaches the optimal value.
In the above motor fault signal feature extraction system, the calculation module is further specifically configured to:
calculating the fitness value corresponding to each particle individual through the fitness function, and comparing the fitness value corresponding to each particle individual with the individual extremum and the global extremum corresponding to each particle individual to obtain a corresponding comparison result;
based on the comparison result, searching corresponding local individuals and globally optimal individuals in a plurality of particle individuals through the PF-PSO algorithm;
updating the inertia weight value of the global optimal individual, and determining the particle position and the particle speed corresponding to the global optimal individual according to the inertia weight value.
A third aspect of the embodiments of the present invention proposes a computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the motor fault signal feature extraction method as described above when executing the computer program.
A fourth aspect of the embodiments of the present invention proposes a storage medium having stored thereon a computer program which, when executed by a processor, implements a motor fault signal feature extraction method as described above.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
Fig. 1 is a flowchart of a motor fault signal feature extraction method according to a first embodiment of the present invention;
fig. 2 is a schematic diagram of a two-channel filter bank in a motor fault signal feature extraction method according to a second embodiment of the present invention;
fig. 3 is a block diagram of a motor fault signal feature extraction system according to a third embodiment of the present invention.
The invention will be further described in the following detailed description in conjunction with the above-described figures.
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. Several embodiments of the invention are presented in the figures. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "mounted" on another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Impact information caused by the existing motor transmission faults is weak, and meanwhile, under the environments of high rotating speed, strong load and strong noise of a motor, the fault characteristics of the motor transmission often show nonlinear and non-stable characteristic information.
Therefore, in order to overcome the shortcomings of the prior art, it is necessary to provide a method capable of extracting the characteristics of the motor transmission fault signal under the complex working condition so as to analyze the cause of the motor transmission fault.
Referring to fig. 1, a motor fault signal feature extraction method provided by a first embodiment of the present invention is shown, and the motor fault signal feature extraction method provided by the present embodiment can introduce the penalty function idea in the PF-PSO algorithm into the RSSD algorithm, so that the optimized RSSD algorithm has a fast convergence speed and a good adaptability, so that the required fault feature information can be simply and quickly extracted from the fault signal, which is beneficial to the wide-range use of the motor transmission device.
Specifically, the method for extracting the motor fault signal features provided by the embodiment specifically includes the following steps:
step S10, when a fault signal is detected, initializing parameters in an RSSD algorithm and a PF-PSO algorithm at the same time, and calculating optimal parameters adapted to the RSSD algorithm through the PF-PSO algorithm based on a preset rule, wherein the optimal parameters have uniqueness;
Specifically, in this embodiment, it should be first noted that, the method for extracting a motor fault signal feature provided in this embodiment is specifically applied to a motor transmission device, and is further configured to perform feature extraction on a fault signal generated when the motor transmission device fails, so as to correspondingly detect a cause of the motor transmission device failure, thereby performing corresponding maintenance.
In addition, in the present embodiment, it should be noted that the motor fault signal feature extraction method provided in the present embodiment is implemented based on a PF-PSO (penalty function particle swarm optimization) algorithm and an RSSD (resonance sparse decomposition) algorithm, and the PF-PSO algorithm and the RSSD algorithm provided in the present embodiment can be used in combination.
Based on this, it should be noted that, in this step, when the fault signal generated by the motor transmission device is detected in real time in this step, the parameters in the RSSD algorithm and the PF-PSO algorithm are initialized first, based on this, the optimal parameters adapted to the RSSD algorithm are calculated according to the preset rule and through the PF-PSO algorithm, and specifically, the optimal parameters provided in this embodiment have uniqueness, that is, only one optimal parameter.
Step S20, inputting the optimal parameters into the RSSD algorithm so that the RSSD algorithm outputs a corresponding optimal low-resonance component signal;
further, in this embodiment, after the required optimal parameters are obtained through the steps, the step further inputs the optimal parameters into the RSSD algorithm, so that the RSSD algorithm further outputs the corresponding optimal low-resonance component signals.
And step S30, performing fault characteristic identification processing on the optimal low-resonance component signal so as to correspondingly extract fault characteristic information corresponding to the fault signal.
Finally, in this step, after the optimal low-resonance component signal is obtained, this step further performs a fault feature recognition process on the optimal low-resonance component signal, so that fault feature information corresponding to the fault signal can be further extracted.
When the method is used, when a fault signal is detected, parameters in an RSSD algorithm and a PF-PSO algorithm are initialized at the same time, and an optimal parameter matched with the RSSD algorithm is calculated through the PF-PSO algorithm based on a preset rule, wherein the optimal parameter is unique; further, inputting the optimal parameters into an RSSD algorithm so that the RSSD algorithm outputs a corresponding optimal low-resonance component signal; and finally, performing fault characteristic identification processing on the optimal low-resonance component signal to correspondingly extract fault characteristic information corresponding to the fault signal. By the method, the penalty function idea in the PF-PSO algorithm can be introduced into the RSSD algorithm, so that the optimized RSSD algorithm has higher convergence speed and better adaptability, required fault characteristic information can be simply and rapidly extracted from fault signals, and the method is beneficial to the wide-range use of motor transmission devices.
It should be noted that the foregoing implementation procedure is only for illustrating the feasibility of the present application, but this does not represent that the motor fault signal feature extraction method of the present application has only one implementation procedure, and instead, the motor fault signal feature extraction method of the present application may be incorporated into the feasible embodiments of the present application as long as it can be implemented.
In summary, the motor fault signal feature extraction method provided by the embodiment of the invention can introduce the penalty function idea in the PF-PSO algorithm into the RSSD algorithm, so that the optimized RSSD algorithm has higher convergence speed and better adaptability, and the required fault feature information can be simply and rapidly extracted from the fault signal, thereby being beneficial to the large-scale use of the motor transmission device.
The second embodiment of the present invention also provides a motor fault signal feature extraction method, where the motor fault signal feature extraction method provided in the present embodiment is different from the motor fault signal feature extraction method provided in the first embodiment described above in that:
specifically, in this embodiment, it should be noted that, the step of calculating, by the PF-PSO algorithm, the optimal parameter adapted to the RSSD algorithm based on the preset rule includes:
Detecting a plurality of penalty function particle populations contained in the PF-PSO algorithm, and decomposing the penalty function particle populations through the RSSD algorithm to generate a plurality of corresponding particle individuals;
iteratively updating the particle positions of a plurality of particle individuals based on a low resonance component signal CK minimum principle, and judging whether the particle positions corresponding to the updated particle individuals meet preset constraint conditions or not in real time;
and if the particle positions corresponding to the updated particle individuals meet the constraint conditions, judging that the particle positions corresponding to the current particle individuals are the optimal parameters.
Specifically, in this embodiment, it should be noted that, the PF-PSO algorithm provided in this embodiment is specifically configured by a plurality of penalty function particle populations, based on this, in this embodiment, a plurality of penalty function particle populations included in the current PF-PSO algorithm are first detected, and the current plurality of penalty function particle populations are further decomposed by the RSSD algorithm, so that a plurality of particle individuals can be correspondingly split.
Furthermore, in this embodiment, the particle positions of the current particle units are iteratively updated according to a preset minimum rule based on the low-resonance component signal CK, and at the same time, whether the particle positions corresponding to the updated particle units meet a preset constraint condition is determined in real time, and specifically, if the particle positions corresponding to the updated particle units meet the constraint condition is determined in real time, the value of the particle positions corresponding to the current particle units is correspondingly determined to be the optimal parameter.
In this embodiment, as shown in fig. 2, it should be noted that, in the resonance sparse decomposition method provided in this embodiment, a corresponding two-pass filter bank is established by selecting an appropriate quality factor through wavelet transformation using an adjustable quality factor, so that wavelet basis function sets corresponding to different components can be obtained through the two-pass filter bank, based on this, different frequency conversion coefficients can be further obtained, so that different component signals can be finally obtained, so as to correspondingly complete decomposition processing on the penalty function particle population. Wherein, in the present embodiment, as shown in FIG. 2, whereinx(n) For the original input signal, the signal is processed,H 0 (ω) And (3) withH 1 (ω) Representing a low-pass filter and a high-pass filter respectively,
and->
Respectively representH 0 (ω) And (3) withH 1 (ω) Is divided into signals by high and low pass filtersv 0 (n) And (3) withv 1 (n) And pass->
And->
Will bev 0 (n) And (3) withv 1 (n) Collectively referred to as the desired signaly(n) It should be noted that, in the resonance sparse decomposition method provided in this embodiment, a corresponding two-pass filter set is established by using wavelet transform of an adjustable quality factor to select an appropriate quality factor, so that wavelet basis function sets corresponding to different components can be obtained through the two-pass filter set, and based on the wavelet basis function sets, different frequency conversion coefficients can be further obtained, so that different component signals can be finally obtained, and the decomposition processing of the penalty function particle population can be correspondingly completed.
Further, in this embodiment, it should be noted that, when the fault signal is detected, the step of initializing parameters in the RSSD algorithm and the PF-PSO algorithm simultaneously includes:
when the fault signal is detected, initializing penalty function particle population parameters in the PF-PSO algorithm, and randomly generating a plurality of penalty function particle populations;
and selecting quality factors corresponding to the penalty function particle populations, and setting optimizing intervals corresponding to the quality factors, wherein the optimizing intervals have uniqueness.
Further, in this embodiment, in order to accurately process the detected fault signal, the embodiment initializes the penalty function particle population parameter in the PF-PSO algorithm in real time, and randomly generates a plurality of corresponding penalty function particle populations, and based on this, the embodiment further selects a quality factor corresponding to the current plurality of penalty function particle populations, and at the same time, sets an optimization interval corresponding to the quality factor, where the optimization interval has uniqueness.
It should be noted that, the penalty function particle population provided in this embodiment specifically includes parameters such as a particle number, a learning factor, a maximum weight coefficient, a maximum iteration coefficient, and a penalty function factor, and based on the parameters, different particle populations can be randomly generated, and meanwhile, in this embodiment, the optimizing intervals of the high quality factor and the low quality factor are respectively [3, 15] and [1,3], and based on this, the detection range of the fault signal can be effectively limited, so as to further improve the detection accuracy.
In addition, it should be noted that the magnitude of the quality factor is related to the oscillation frequency of the wavelet transform of the adjustable quality factor, and the core problem of separating out the fault impact signal by resonance sparse decomposition in this embodiment is whether the wavelet transform basis function waveform of the adjustable quality factor and the fault impact component waveform can be accurately fitted, so determining the proper value of the quality factor can further ensure the capability of the adjustable quality factor transform to characterize the fault impact component.
In addition, in the present embodiment, it should be noted that the above-described low resonance component signal CK-based minima principle includes:
selecting a correlation coefficient C and a kurtosis factor K which are matched with the PF-PSO, and establishing a mapping relation between the correlation coefficient C and the kurtosis factor K;
performing fusion operation on the correlation coefficient C and the kurtosis factor K to generate a corresponding low-resonance component signal CK, and setting the low-resonance component signal CK as an adaptability function of the PF-PSO algorithm;
wherein, the expression of the kurtosis factor is:
wherein μ represents the mean value of the signal, σ represents the standard deviation, E represents the expected value, and the correlation coefficient C has the following expression:
wherein x is i And y i Respectively representing the value of the current signal x, y at the i-th point,
and->
Respectively represent the average value of the current signals x and y, and the correlation coefficient C E [0,1 ]]When the correlation coefficient c=0, it indicates that the signal x is completely uncorrelated with the signal y, and when the correlation coefficient c=1, it indicates that the signal x is completely correlated with the signal y, and n indicates a constant, and the low resonance component signal CK is defined as:
CK=C/K
when the correlation coefficient reaches the minimum value, the low resonance component signal reaches the minimum value at the same time, and the decomposition effect of the RSSD algorithm reaches the optimal value.
In addition, in this embodiment, the low resonance component signal CK of the correlation coefficient C and the kurtosis factor K is introduced as the fitness function of the particle swarm algorithm of the penalty function, where the kurtosis value of the fault signal can accurately reflect the impact characteristic of the fault signal, specifically, the higher the kurtosis value of the fault signal, the stronger the impact characteristic corresponding to the fault signal, and conversely, the weaker the impact characteristic corresponding to the fault signal. However, considering only the kurtosis factor K as the fitness function of the penalty function particle swarm optimization algorithm ignores impact component signals having high individual amplitudes and a wide distribution. Based on this, the present embodiment further introduces the above-described correlation coefficient C to correspondingly constrain the above-described kurtosis factor K.
In addition, in this embodiment, it should be further noted that the step of iteratively updating the particle positions of the plurality of particle units based on the low resonance component signal CK minima principle includes:
calculating the fitness value corresponding to each particle individual through the fitness function, and comparing the fitness value corresponding to each particle individual with the individual extremum and the global extremum corresponding to each particle individual to obtain a corresponding comparison result;
based on the comparison result, searching corresponding local individuals and globally optimal individuals in a plurality of particle individuals through the PF-PSO algorithm;
updating the inertia weight value of the global optimal individual, and determining the particle position and the particle speed corresponding to the global optimal individual according to the inertia weight value.
In addition, in this embodiment, it should be further noted that, after the required fitness function is obtained through the above steps, the embodiment further calculates the fitness value corresponding to each particle unit according to the fitness function, and at the same time, compares the fitness value corresponding to each particle unit with the individual extremum and the global extremum corresponding to each particle unit, and obtains the corresponding comparison result.
Based on the above, the corresponding local individual and global optimal individual can be simply and effectively found out from the particle individuals, and on the basis, the particle position and the particle speed corresponding to the global optimal individual can be immediately determined according to the inertia weight value only by further updating the inertia weight value of the current global optimal individual.
Further, in the present embodiment, it is to be noted that, in the initial stage of particle swarm optimization, the particles have a larger self-learning ability and a smaller social learning ability, so that global searching ability needs to be enhanced, and in the later stage of algorithm optimization, the particles have a larger social learning ability and a smaller self-searching ability, so that convergence effect needs to be enhanced. In addition, due to the learning factor c 1 And c 2 The collaborative inertia weight omega controls the algorithm to evolve towards the optimal solution direction. Therefore, the present embodiment requires the learning factor c 1 And c 2 And the inertial weight ω. Specifically, the improved algorithm provided in this embodiment is:
wherein omega max And omega min Respectively representing the maximum value and the minimum value of the inertia weight omega, t represents the current iteration number, t max Represents the maximum number of iterations, c 1in And c 2in Respectively represent learning factors c 1 And c 2 Initial value of c 1fin And c 2fin Respectively represent learning factors c 1 And c 2 Final value of (2).
In addition, in this embodiment, it should also be noted that, the core idea of the penalty function particle swarm optimization algorithm provided in this embodiment is to convert the constraint optimization problem into an unconstrained problem to solve, i.e. to penalize the unfulfilled condition and the unfeasible point attempting to cross the constraint condition, and force the unfeasible point to approach. The construction idea is to add a penalty term into the original objective function so as to obtain a new objective function, thereby converting the constraint optimization problem into an unconstrained optimization problem.
In particular, for optimization problems<A，f>Wherein A is expressed as a feasible solution of the constraint condition, f: A-R n Represented asOptimization object of objective function. Thus, the solution expression for the target object minf (x) can be derived as:
wherein n is a constant, x is a variable, j is a coefficient, G j (x) For the j-th constraint, K, m each represent a constant, based on which the solution expression described above is transformed into after introducing the penalty function particle population optimization algorithm described above:
wherein F (x, M) represents a penalty function, M represents a penalty factor, which is a positive constant, mp (x) represents a penalty term, and specifically, when M is sufficiently large, the optimal solution of F (x, M) can approach the optimal solution of the constraint problem, based on which the function F (x, M) does not penalize feasible points but penalizes non-feasible points, thereby being capable of converting the problem of solving the constraint extremum into the problem of solving the unconstrained extremum.
It should be noted that, for the sake of brevity, the method according to the second embodiment of the present invention, which implements the same principle and some of the technical effects as the first embodiment, is not mentioned here, and reference is made to the corresponding content provided by the first embodiment.
In summary, the motor fault signal feature extraction method provided by the embodiment of the invention can introduce the penalty function idea in the PF-PSO algorithm into the RSSD algorithm, so that the optimized RSSD algorithm has higher convergence speed and better adaptability, and the required fault feature information can be simply and rapidly extracted from the fault signal, thereby being beneficial to the large-scale use of the motor transmission device.
Referring to fig. 3, a motor fault signal feature extraction system according to a third embodiment of the present invention is shown, the system includes:
the computing module 12 is configured to initialize parameters in an RSSD algorithm and a PF-PSO algorithm at the same time when a fault signal is detected, and calculate an optimal parameter adapted to the RSSD algorithm through the PF-PSO algorithm based on a preset rule, where the optimal parameter has uniqueness;
an output module 22, configured to input the optimal parameter into the RSSD algorithm, so that the RSSD algorithm outputs a corresponding optimal low-resonance component signal;
And the extracting module 32 is configured to perform fault feature identification processing on the optimal low-resonance component signal, so as to correspondingly extract fault feature information corresponding to the fault signal.
In the above motor fault signal feature extraction system, the computing module 12 is specifically configured to:
detecting a plurality of penalty function particle populations contained in the PF-PSO algorithm, and decomposing the penalty function particle populations through the RSSD algorithm to generate a plurality of corresponding particle individuals;
iteratively updating the particle positions of a plurality of particle individuals based on a low resonance component signal CK minimum principle, and judging whether the particle positions corresponding to the updated particle individuals meet preset constraint conditions or not in real time;
and if the particle positions corresponding to the updated particle individuals meet the constraint conditions, judging that the particle positions corresponding to the current particle individuals are the optimal parameters.
In the above motor fault signal feature extraction system, the computing module 12 is further specifically configured to:
when the fault signal is detected, initializing penalty function particle population parameters in the PF-PSO algorithm, and randomly generating a plurality of penalty function particle populations;
And selecting quality factors corresponding to the penalty function particle populations, and setting optimizing intervals corresponding to the quality factors, wherein the optimizing intervals have uniqueness.
In the above motor fault signal feature extraction system, the low resonance component signal CK-based minima principle includes:
selecting a correlation coefficient C and a kurtosis factor K which are matched with the PF-PSO, and establishing a mapping relation between the correlation coefficient C and the kurtosis factor K;
performing fusion operation on the correlation coefficient C and the kurtosis factor K to generate a corresponding low-resonance component signal CK, and setting the low-resonance component signal CK as an adaptability function of the PF-PSO algorithm;
wherein, the expression of the kurtosis factor is:
wherein μ represents the mean value of the signal, σ represents the standard deviation, E represents the expected value, and the correlation coefficient C has the following expression:
wherein, the correlation coefficient C e [0,1] indicates that the signal x is completely uncorrelated with the signal y when the correlation coefficient c=0, and indicates that the signal x is completely correlated with the signal y when the correlation coefficient c=1, n indicates a constant, and the definition formula of the low resonance component signal CK is:
CK=C/K
when the correlation coefficient reaches the minimum value, the low resonance component signal reaches the minimum value at the same time, and the decomposition effect of the RSSD algorithm reaches the optimal value.
In the above motor fault signal feature extraction system, the computing module 12 is further specifically configured to:
calculating the fitness value corresponding to each particle individual through the fitness function, and comparing the fitness value corresponding to each particle individual with the individual extremum and the global extremum corresponding to each particle individual to obtain a corresponding comparison result;
based on the comparison result, searching corresponding local individuals and globally optimal individuals in a plurality of particle individuals through the PF-PSO algorithm;
updating the inertia weight value of the global optimal individual, and determining the particle position and the particle speed corresponding to the global optimal individual according to the inertia weight value.
A fourth embodiment of the present invention provides a computer including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the motor fault signal feature extraction method provided in the above embodiment when executing the computer program.
A fifth embodiment of the present invention provides a storage medium having stored thereon a computer program which, when executed by a processor, implements the motor fault signal feature extraction method provided by the above embodiments.
In summary, the method, the system, the computer and the storage medium for extracting the motor fault signal feature provided by the embodiment of the invention can introduce the penalty function idea in the PF-PSO algorithm into the RSSD algorithm, so that the optimized RSSD algorithm has higher convergence speed and better adaptability, and the needed fault feature information can be simply and rapidly extracted from the fault signal, thereby being beneficial to the wide-range use of the motor transmission device.
The above-described respective modules may be functional modules or program modules, and may be implemented by software or hardware. For modules implemented in hardware, the various modules described above may be located in the same processor; or the above modules may be located in different processors in any combination.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. A method for extracting motor fault signal characteristics, the method comprising:
When a fault signal is detected, initializing parameters in an RSSD algorithm and a PF-PSO algorithm at the same time, and calculating optimal parameters matched with the RSSD algorithm through the PF-PSO algorithm based on a preset rule, wherein the optimal parameters have uniqueness;
inputting the optimal parameters into the RSSD algorithm so that the RSSD algorithm outputs a corresponding optimal low-resonance component signal;
and carrying out fault characteristic identification processing on the optimal low-resonance component signal so as to correspondingly extract fault characteristic information corresponding to the fault signal.
2. The motor fault signal feature extraction method according to claim 1, characterized in that: the step of calculating the optimal parameters adapted to the RSSD algorithm by the PF-PSO algorithm based on preset rules includes:
detecting a plurality of penalty function particle populations contained in the PF-PSO algorithm, and decomposing the penalty function particle populations through the RSSD algorithm to generate a plurality of corresponding particle individuals;
iteratively updating the particle positions of a plurality of particle individuals based on a low resonance component signal CK minimum principle, and judging whether the particle positions corresponding to the updated particle individuals meet preset constraint conditions or not in real time;
And if the particle positions corresponding to the updated particle individuals meet the preset constraint conditions, judging that the particle positions corresponding to the current particle individuals are the optimal parameters.
3. The motor fault signal feature extraction method according to claim 2, characterized in that: the step of initializing parameters in the RSSD algorithm and the PF-PSO algorithm simultaneously when the fault signal is detected comprises the following steps:
when the fault signal is detected, initializing penalty function particle population parameters in the PF-PSO algorithm, and randomly generating a plurality of penalty function particle populations;
and selecting quality factors corresponding to the penalty function particle populations, and setting optimizing intervals corresponding to the quality factors, wherein the optimizing intervals have uniqueness.
4. The motor fault signal feature extraction method according to claim 2, characterized in that: the low resonance component signal CK-based minima principle includes:
selecting a correlation coefficient C and a kurtosis factor K which are matched with the PF-PSO algorithm, and establishing a mapping relation between the correlation coefficient C and the kurtosis factor K;
performing fusion operation on the correlation coefficient C and the kurtosis factor K to generate a corresponding low-resonance component signal CK, and setting the low-resonance component signal CK as an adaptability function of the PF-PSO algorithm;
Wherein, the expression of the kurtosis factor is:
wherein μ represents the mean value of the signal, σ represents the standard deviation, E represents the expected value, and the correlation coefficient C has the following expression:
wherein x is i And y i Respectively representing the value of the current signal x, y at the i-th point,
and->
Respectively represent the average value of the current signals x and y, and the correlation coefficient C E [0,1 ]]When the correlation coefficient c=0, it indicates that the signal x is completely uncorrelated with the signal y, and when the correlation coefficient c=1, it indicates that the signal x is completely correlated with the signal y, and n indicates a constant, and the low resonance component signal CK is defined as:
CK=C/K
when the correlation coefficient reaches the minimum value, the low resonance component signal reaches the minimum value at the same time, and the decomposition effect of the RSSD algorithm reaches the optimal value.
5. The motor fault signal feature extraction method according to claim 4, wherein: the step of iteratively updating the particle positions of a plurality of individual particles based on the low resonance component signal CK minima principle comprises:
calculating the fitness value corresponding to each particle individual through the fitness function, and comparing the fitness value corresponding to each particle individual with the individual extremum and the global extremum corresponding to each particle individual to obtain a corresponding comparison result;
Based on the comparison result, searching corresponding local individuals and globally optimal individuals in a plurality of particle individuals through the PF-PSO algorithm;
updating the inertia weight value of the global optimal individual, and determining the particle position and the particle speed corresponding to the global optimal individual according to the inertia weight value.
6. A motor fault signal feature extraction system, the system comprising:
the calculation module is used for initializing parameters in an RSSD algorithm and a PF-PSO algorithm at the same time when a fault signal is detected, and calculating optimal parameters matched with the RSSD algorithm through the PF-PSO algorithm based on a preset rule, wherein the optimal parameters have uniqueness;
the output module is used for inputting the optimal parameters into the RSSD algorithm so that the RSSD algorithm outputs a corresponding optimal low-resonance component signal;
and the extraction module is used for carrying out fault characteristic identification processing on the optimal low-resonance component signal so as to correspondingly extract fault characteristic information corresponding to the fault signal.
7. The motor fault signal feature extraction system of claim 6, wherein: the computing module is specifically configured to:
Detecting a plurality of penalty function particle populations contained in the PF-PSO algorithm, and decomposing the penalty function particle populations through the RSSD algorithm to generate a plurality of corresponding particle individuals;
iteratively updating the particle positions of a plurality of particle individuals based on a low resonance component signal CK minimum principle, and judging whether the particle positions corresponding to the updated particle individuals meet preset constraint conditions or not in real time;
and if the particle positions corresponding to the updated particle individuals meet the preset constraint conditions, judging that the particle positions corresponding to the current particle individuals are the optimal parameters.
8. The motor fault signal feature extraction system of claim 7, wherein: the computing module is also specifically configured to:
when the fault signal is detected, initializing penalty function particle population parameters in the PF-PSO algorithm, and randomly generating a plurality of penalty function particle populations;
and selecting quality factors corresponding to the penalty function particle populations, and setting optimizing intervals corresponding to the quality factors, wherein the optimizing intervals have uniqueness.
9. A computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the motor fault signal feature extraction method of any one of claims 1 to 5 when the computer program is executed.
10. A storage medium having stored thereon a computer program, which when executed by a processor implements the motor fault signal feature extraction method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310582559.9A CN116304649A (en) | 2023-05-23 | 2023-05-23 | Motor fault signal feature extraction method, system, computer and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310582559.9A CN116304649A (en) | 2023-05-23 | 2023-05-23 | Motor fault signal feature extraction method, system, computer and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116304649A true CN116304649A (en) | 2023-06-23 |
Family
ID=86785450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310582559.9A Withdrawn CN116304649A (en) | 2023-05-23 | 2023-05-23 | Motor fault signal feature extraction method, system, computer and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116304649A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116796574A (en) * | 2023-08-23 | 2023-09-22 | 江西五十铃汽车有限公司 | Vibration noise optimization method and system for driving motor |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111693279A (en) * | 2020-05-22 | 2020-09-22 | 电子科技大学 | Mechanical fault diagnosis method based on MPGA parametric resonance sparse decomposition |
| CN115628906A (en) * | 2022-10-08 | 2023-01-20 | 北京理工大学 | Bearing fault diagnosis method based on GA-VMD and self-adaptive stochastic resonance |
| CN115791169A (en) * | 2022-11-22 | 2023-03-14 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Rolling bearing fault diagnosis method and device and electronic equipment |
-
2023
- 2023-05-23 CN CN202310582559.9A patent/CN116304649A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111693279A (en) * | 2020-05-22 | 2020-09-22 | 电子科技大学 | Mechanical fault diagnosis method based on MPGA parametric resonance sparse decomposition |
| CN115628906A (en) * | 2022-10-08 | 2023-01-20 | 北京理工大学 | Bearing fault diagnosis method based on GA-VMD and self-adaptive stochastic resonance |
| CN115791169A (en) * | 2022-11-22 | 2023-03-14 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Rolling bearing fault diagnosis method and device and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| 吴进;陈燕平;周海燕;: "一种滚动轴承故障特征提取方法研究", 海峡科技与产业, no. 01, pages 98 - 100 * |
| 龚永涛;肖涵;易灿灿;: "基于粒子群优化的共振稀疏分解在轴承故障诊断中的应用", 机械设计与制造, no. 04, pages 21 - 25 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116796574A (en) * | 2023-08-23 | 2023-09-22 | 江西五十铃汽车有限公司 | Vibration noise optimization method and system for driving motor |
| CN116796574B (en) * | 2023-08-23 | 2023-12-29 | 江西五十铃汽车有限公司 | Vibration noise optimization method and system for driving motor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116304649A (en) | Motor fault signal feature extraction method, system, computer and storage medium | |
| Carbajal-Hernández et al. | Classification of unbalance and misalignment in induction motors using orbital analysis and associative memories | |
| CN112084505A (en) | Deep learning model malicious sample detection method, system, device and storage medium | |
| KR102289212B1 (en) | Fault diagnosis apparatus and method based on artificial intelligence technology | |
| CN112989906A (en) | Optical fiber perimeter signal feature identification method based on improved integrated empirical mode decomposition and XGboost model | |
| CN117030129A (en) | Paper cup on-line leakage detection method and system thereof | |
| Yan et al. | Fault estimation for single output nonlinear systems using an adaptive sliding mode estimator | |
| Fang et al. | Self-supervised intermittent fault detection for analog circuits guided by prior knowledge | |
| Ogar et al. | The use of artificial neural network for low latency of fault detection and localisation in transmission line | |
| Lopes et al. | New algorithm for identification of discrete-time switched linear systems | |
| CN115878992A (en) | Monitoring method and monitoring system for comprehensive pipe rack power supply system | |
| Bilski et al. | Rough-sets-based reduction for analog systems diagnostics | |
| Xi et al. | Type identification and time location of multiple power quality disturbances based on KF‐ML‐aided DBN | |
| CN115514620B (en) | Anomaly detection method and cloud network platform | |
| Alghassi et al. | Machine performance monitoring and fault classification using vibration frequency analysis | |
| CN108761250B (en) | Industrial control equipment voltage and current-based intrusion detection method | |
| CN108664936B (en) | Diagnosis method and system based on machine fault | |
| Qian et al. | Identification of conductive leakage signal in power cable based on multi-classification PSO-SVM | |
| Zhang et al. | Edge detection by adaptive neuro-fuzzy inference system | |
| CN115774147A (en) | Deep learning-based electric energy metering method, system, equipment and storage medium | |
| Singh et al. | A novel fault classification‐based fault‐tolerant control for two degree of freedom helicopter systems | |
| Rauber et al. | Automatic diagnosis of submersible motor pump conditions in offshore oil exploration | |
| Yan et al. | Infrared image segment and fault location for power equipment | |
| Win et al. | Comparison of Power Quality Disturbances Classification Based on Neural Network | |
| CN114114910B (en) | Model-data hybrid drive-based dynamic anomaly detection method for electric power industrial control 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: 20230623 |
|
| WW01 | Invention patent application withdrawn after publication |